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

    Neuronpedia

    INDEX
    Explanations

    references to water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.93
    Personensuche
    -0.83
     فريبيس
    -0.75
    ientôt
    -0.73
     незавершена
    -0.73
    例句
    -0.73
     يتيمه
    -0.70
     ModelExpression
    -0.69
     <<<<<<<<<<<<<<
    -0.64
    Xna
    -0.64
    POSITIVE LOGITS
     water
    0.90
    water
    0.86
     Water
    0.85
    Water
    0.82
     WATER
    0.66
     воды
    0.63
    水
    0.63
     agua
    0.61
    WATER
    0.61
     água
    0.60
    Act Density 0.157%

    No Known Activations