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

    Neuronpedia

    INDEX
    Explanations

    strong language and expressions of frustration or anger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lähe
    -0.74
     avulla
    -0.72
    ::~
    -0.71
     كومونز
    -0.70
    viewType
    -0.70
    ExtendWith
    -0.69
    lewati
    -0.66
     vastaan
    -0.65
    hadapi
    -0.65
     Rial
    -0.64
    POSITIVE LOGITS
     fucking
    1.08
    fuck
    1.01
     damn
    0.98
    fucking
    0.98
     goddamn
    0.96
     fuck
    0.95
     Fucking
    0.94
    Fucking
    0.94
    FUCK
    0.94
     Fuck
    0.93
    Act Density 0.094%

    No Known Activations