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

    Neuronpedia

    INDEX
    Explanations

    phrases related to complex interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APO
    -0.14
    SSIP
    -0.14
    URRE
    -0.13
    _utf
    -0.13
    à¥Įड
    -0.13
    .tokenize
    -0.12
    ÙĦÙģ
    -0.12
    ãĢĤä»Ĭ
    -0.12
    lal
    -0.12
    vard
    -0.12
    POSITIVE LOGITS
    immel
    0.18
    idor
    0.17
    gest
    0.15
    ean
    0.14
    ìį¨
    0.14
    estro
    0.14
    Łèĥ½
    0.14
    oner
    0.13
    eyer
    0.13
     verdict
    0.13
    Act Density 0.053%

    No Known Activations