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

    Neuronpedia

    INDEX
    Explanations

    concepts related to morality and ethical behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vegli
    -0.45
    ゴン
    -0.44
     seguridad
    -0.40
    局
    -0.39
    不利
    -0.39
    Success
    -0.38
    ZoneId
    -0.38
     tuta
    -0.37
     decidieron
    -0.37
     navigator
    -0.37
    POSITIVE LOGITS
     مشين
    0.93
    ]")]
    0.83
    0.74
    دانشنامهٔ
    0.73
    uxxxx
    0.73
    expandindo
    0.69
     كومونز
    0.67
    contentLoaded
    0.67
    MLLoader
    0.65
    PreferredItem
    0.64
    Act Density 0.199%

    No Known Activations