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

    Neuronpedia

    INDEX
    Explanations

    code structures and commands related to data handling and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused74>
    -0.80
    <unused16>
    -0.80
    <unused41>
    -0.80
     queſta
    -0.80
    <unused8>
    -0.80
    <unused43>
    -0.79
    <unused79>
    -0.79
    <unused14>
    -0.79
    <unused3>
    -0.79
    [@BOS@]
    -0.79
    POSITIVE LOGITS
     them
    0.44
    <eos>
    0.38
     respiración
    0.35
     comprado
    0.34
     these
    0.34
     this
    0.34
     тот
    0.32
     hablado
    0.31
     those
    0.30
     hielo
    0.29
    Act Density 0.267%

    No Known Activations