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

    Neuronpedia

    INDEX
    Explanations

    terms related to analysis and analytical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acters
    -0.16
    ebek
    -0.15
    ingroup
    -0.14
    JECTED
    -0.14
    æł¼
    -0.14
    reator
    -0.14
    noc
    -0.14
    bagai
    -0.14
    lain
    -0.14
    pared
    -0.14
    POSITIVE LOGITS
    yses
    0.19
    ogue
    0.18
    YSIS
    0.18
    conda
    0.17
    ysts
    0.17
    yy
    0.16
    phabet
    0.16
     IReadOnly
    0.15
    yc
    0.15
     mil
    0.15
    Act Density 0.014%

    No Known Activations