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

    Neuronpedia

    INDEX
    Explanations

    instances of strong verbs and adjectives indicating actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .weixin
    -0.20
    ensch
    -0.15
    ãĥ¼ãĥĬ
    -0.15
    'gc
    -0.14
    ifo
    -0.14
    ocities
    -0.14
    ctal
    -0.14
    unfinished
    -0.14
    uncture
    -0.14
     fikir
    -0.14
    POSITIVE LOGITS
    ilon
    0.17
     panel
    0.16
    meli
    0.15
    atta
    0.15
     Panel
    0.15
    _CODEC
    0.14
     dem
    0.14
    ault
    0.14
    ario
    0.14
     Gal
    0.14
    Act Density 0.045%

    No Known Activations