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

    Neuronpedia

    INDEX
    Explanations

    references to significant numerical data or values in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.42
     Efq
    -1.41
     themſelves
    -1.40
     myſelf
    -1.36
     raiſ
    -1.35
    ^(@)
    -1.30
     itſelf
    -1.30
     ſeveral
    -1.28
    ſelves
    -1.26
     purpoſe
    -1.26
    POSITIVE LOGITS
     (
    0.71
    ing
    0.70
     [
    0.64
     /
    0.63
    ↵↵
    0.61
     -
    0.58
    <eos>
    0.58
     –
    0.58
     nos
    0.57
    ent
    0.55
    Act Density 0.944%

    No Known Activations