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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negotiation, exceptions, or conditions related to rules and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.17
    udder
    -0.17
    apid
    -0.16
    eker
    -0.16
    oren
    -0.15
    hsi
    -0.14
    oris
    -0.14
    iese
    -0.14
    ullan
    -0.14
    İ
    -0.14
    POSITIVE LOGITS
     circum
    0.20
     otherwise
    0.18
     exceptions
    0.17
     forced
    0.17
     Otherwise
    0.16
     overcome
    0.16
     Schwe
    0.15
     overcoming
    0.15
    natal
    0.15
    ritch
    0.15
    Act Density 0.020%

    No Known Activations