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

    Neuronpedia

    INDEX
    Explanations

    symbols related to ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ities
    -0.17
    wand
    -0.15
    ainties
    -0.15
    ERCHANT
    -0.15
    loi
    -0.14
    gue
    -0.14
    indir
    -0.14
    ÑĭÑĤ
    -0.13
    loha
    -0.13
    ogn
    -0.13
    POSITIVE LOGITS
    er
    0.26
    a
    0.23
    s
    0.22
    e
    0.20
    y
    0.20
    es
    0.19
    //{{
    0.19
    ing
    0.18
    eck
    0.17
    erer
    0.16
    Act Density 0.037%

    No Known Activations