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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules or conditions surrounding behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ·
    -0.17
    inkel
    -0.17
    Line
    -0.15
    neys
    -0.15
    è¬Ŀ
    -0.14
    prises
    -0.14
     Abstract
    -0.14
    immel
    -0.14
    andel
    -0.14
    strup
    -0.14
    POSITIVE LOGITS
    zw
    0.16
    é©
    0.15
    ĭ
    0.15
     Jame
    0.14
    zm
    0.14
    iar
    0.14
    cie
    0.14
    aves
    0.14
     Jad
    0.14
    Creators
    0.13
    Act Density 0.010%

    No Known Activations