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

    Neuronpedia

    INDEX
    Explanations

    references to legal and governmental terms or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     narci
    -0.40
     crees
    -0.39
     Unterhaltung
    -0.35
    Y
    -0.34
    z
    -0.34
     garota
    -0.34
    zen
    -0.34
     
    -0.34
    on
    -0.34
    rest
    -0.34
    POSITIVE LOGITS
     houſe
    0.86
     Jefus
    0.83
     Houſe
    0.81
    ſelf
    0.81
     myſelf
    0.80
     himſelf
    0.77
     Monfieur
    0.74
     itſelf
    0.74
     Anſ
    0.73
     pleaſure
    0.73
    Act Density 1.121%

    No Known Activations