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

    Neuronpedia

    INDEX
    Explanations

    nouns and terms related to societal issues and organization structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailability
    -0.14
     Twe
    -0.14
     IID
    -0.14
    shan
    -0.14
     lod
    -0.14
    ptype
    -0.14
     sp
    -0.14
    -preview
    -0.13
     SHA
    -0.13
     Spr
    -0.13
    POSITIVE LOGITS
    warz
    0.17
     winters
    0.16
    vro
    0.15
    arResult
    0.15
    _PKG
    0.15
    inho
    0.14
    cko
    0.14
     seasons
    0.14
    alc
    0.14
    ses
    0.14
    Act Density 0.018%

    No Known Activations