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

    Neuronpedia

    INDEX
    Explanations

    words related to indigenous cultures or countries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     moze
    -0.59
    cheidet
    -0.52
     jeste
    -0.50
     zove
    -0.48
     najbolj
    -0.47
    Grath
    -0.47
    )_/¯
    -0.46
     kobieta
    -0.46
    RTLE
    -0.46
     للاسماء
    -0.46
    POSITIVE LOGITS
     Native
    1.04
    Native
    1.03
     native
    1.02
    native
    0.93
    NATIVE
    0.92
     fluo
    0.86
     natives
    0.79
     Mémoires
    0.79
     peculi
    0.77
     Violon
    0.77
    Act Density 0.071%

    No Known Activations