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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section header

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.98
     pleaſure
    -0.95
     houſe
    -0.94
     TextAppearance
    -0.94
     ſtate
    -0.94
     fubject
    -0.93
     raiſ
    -0.90
     itſelf
    -0.90
     purpoſe
    -0.88
    saraba
    -0.88
    POSITIVE LOGITS
     
    0.73
     “
    0.59
     a
    0.57
     "
    0.55
    <eos>
    0.53
     the
    0.53
     must
    0.52
     ha
    0.45
     an
    0.45
    もん
    0.45
    Act Density 0.053%

    No Known Activations