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

    Neuronpedia

    INDEX
    Explanations

    expressions conveying uncertainty or concern about situations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.56
    AnimationsModule
    -0.54
     oamenii
    -0.53
     oameni
    -0.53
    omiast
    -0.52
     muere
    -0.52
    iciens
    -0.52
     %>%
    -0.51
     bellissima
    -0.51
    と言って
    -0.50
    POSITIVE LOGITS
    matchCondition
    0.63
     nakalista
    0.60
     hefty
    0.56
    可不是
    0.54
     foon
    0.53
     compri
    0.51
    økt
    0.50
    |}{}
    0.50
    middels
    0.50
    RenderAtEndOf
    0.50
    Act Density 0.647%

    No Known Activations