Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to health, particularly issues concerning medication and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    This neuron detects phrases describing deficiency, shortage, or reduction, such as "drop", "low level", "depleted", "short", "decline", and "contraction".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    medical conditions, especially related to body measurements and diseases.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.76
     intStringLen
    -0.52
    Bent
    -0.51
    writeFieldEnd
    -0.51
    ?>
    -0.50
     /^[
    -0.49
     Bent
    -0.49
    */].
    -0.49
     EconPapers
    -0.48
     Савезне
    -0.46
    POSITIVE LOGITS
     shortage
    0.58
     kekurangan
    0.57
     manque
    0.55
     missing
    0.54
     mancanza
    0.53
     deficient
    0.52
     manquer
    0.52
     inadequate
    0.50
     starvation
    0.50
     insufficient
    0.50
    Act Density 0.642%

    No Known Activations