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

    Neuronpedia

    INDEX
    Explanations

    references to specific groups or classifications of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.92
     Monfieur
    -0.80
     Efq
    -0.79
    ecap
    -0.76
     Fascism
    -0.75
     faſt
    -0.69
     itſelf
    -0.69
     oreilles
    -0.66
    ChildScrollView
    -0.66
     cleft
    -0.65
    POSITIVE LOGITS
     who
    1.16
     whom
    0.77
     whose
    0.76
    时候
    0.72
    Whose
    0.66
     pesky
    0.65
    ScopeManager
    0.65
    genen
    0.63
     Folks
    0.62
    ionados
    0.62
    Act Density 0.071%

    No Known Activations