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

    Neuronpedia

    INDEX
    Explanations

    words related to interpersonal relationships and societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -equipped
    -0.17
    edBy
    -0.16
     sharp
    -0.16
    kova
    -0.15
    osate
    -0.15
    urator
    -0.14
    amespace
    -0.14
    ovu
    -0.14
    erset
    -0.14
    ات
    -0.14
    POSITIVE LOGITS
    ly
    0.87
    LY
    0.59
    liness
    0.56
    liest
    0.47
    lys
    0.45
    lier
    0.41
    lyph
    0.40
    lies
    0.38
    ely
    0.36
    hood
    0.35
    Act Density 0.090%

    No Known Activations