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

    Neuronpedia

    INDEX
    Explanations

    terms related to identity, social structure, and individualism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.16
    uces
    -0.14
    ìĨĶ
    -0.14
    parable
    -0.14
    ificates
    -0.14
    ographed
    -0.14
    าà¹Ģล
    -0.14
    lys
    -0.13
    ej
    -0.13
    onaut
    -0.13
    POSITIVE LOGITS
    ness
    0.46
    ity
    0.44
    ism
    0.36
    ality
    0.33
    fulness
    0.29
    iness
    0.28
    itude
    0.28
    NESS
    0.28
    hood
    0.28
    ification
    0.27
    Act Density 0.213%

    No Known Activations