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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.70
     
    -0.69
     –
    -0.69
     (
    -0.63
    -
    -0.63
    .
    -0.59
    :
    -0.58
     in
    -0.56
     B
    -0.56
     i
    -0.56
    POSITIVE LOGITS
     myſelf
    1.40
     pleaſure
    1.39
     purpoſe
    1.36
     houſe
    1.34
     itſelf
    1.34
    ſelf
    1.33
     GenerationType
    1.33
     greateſt
    1.24
     Houſe
    1.23
     Anſ
    1.22
    Act Density 0.112%

    No Known Activations