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

    Neuronpedia

    INDEX
    Explanations

    terms related to identity and description of individuals and their traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etics
    -0.14
    phans
    -0.13
    'class
    -0.13
    λλα
    -0.13
    ãĥªãĥ¼ãĤº
    -0.13
    $MESS
    -0.13
    αιν
    -0.13
    TED
    -0.13
    λλά
    -0.13
    igans
    -0.13
    POSITIVE LOGITS
    bote
    0.16
    ä»ĭ
    0.15
    bsite
    0.15
    ynes
    0.14
    olson
    0.14
    ضÙĬ
    0.13
    sgiving
    0.13
    Ñij
    0.13
    .tm
    0.13
    ovky
    0.13
    Act Density 0.203%

    No Known Activations