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

    Neuronpedia

    INDEX
    Explanations

    negative statements about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InitVars
    -0.80
     noqa
    -0.70
    клопе
    -0.68
    RenderAtEndOf
    -0.68
    #+#
    -0.65
     <=",
    -0.64
    DeleteBehavior
    -0.64
     disambiguazione
    -0.58
    AsUp
    -0.58
    Παραπομπές
    -0.57
    POSITIVE LOGITS
     certainly
    0.73
     surely
    0.68
     seems
    0.68
     sounds
    0.65
     sounding
    0.64
    certainly
    0.63
     definitely
    0.62
     rasanya
    0.61
     Certainly
    0.61
     klingt
    0.60
    Act Density 0.430%

    No Known Activations