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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups within a narrative

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

    references to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Racine
    -0.93
     uſe
    -0.86
     cauſe
    -0.83
     purpoſe
    -0.79
     pleaſure
    -0.79
    cys
    -0.77
     ſuch
    -0.77
     leaſt
    -0.75
     Conci
    -0.74
     stiefel
    -0.74
    POSITIVE LOGITS
     him
    1.36
     them
    1.29
     Him
    1.28
    Him
    1.26
     Them
    1.25
     HIM
    1.24
     THEM
    1.20
    them
    1.14
     herself
    1.13
    Them
    1.13
    Act Density 0.121%

    No Known Activations