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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to causes or results in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oub
    -0.16
     base
    -0.15
    wel
    -0.15
     true
    -0.14
     detail
    -0.14
    rm
    -0.14
    lam
    -0.14
     possibility
    -0.14
     distinction
    -0.14
    gun
    -0.13
    POSITIVE LOGITS
    cate
    0.15
    ÑģÑĮ
    0.15
    olate
    0.15
     ValidationResult
    0.14
    adol
    0.14
    rowsable
    0.14
    ëŀ¨
    0.14
    çı
    0.14
    wares
    0.14
     Eug
    0.14
    Act Density 0.015%

    No Known Activations