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

    Neuronpedia

    INDEX
    Explanations

    references to significant physical actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    893
    -0.18
    ptions
    -0.15
    æĨ
    -0.15
    hb
    -0.14
    ñ
    -0.14
    ë¯
    -0.14
     mand
    -0.14
    egrity
    -0.14
    dep
    -0.13
    _ROLE
    -0.13
    POSITIVE LOGITS
    #
    0.15
    енка
    0.15
    anka
    0.14
    atri
    0.14
    encial
    0.14
    μÎŃν
    0.14
    aved
    0.14
    all
    0.14
    IFO
    0.14
    azzi
    0.14
    Act Density 0.397%

    No Known Activations