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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the importance of a subject and providing suggestions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iker
    -0.17
    ustr
    -0.16
    ÑĢоÑģÑĤо
    -0.16
    _controls
    -0.15
     Dün
    -0.15
    iteur
    -0.14
     disarm
    -0.14
    usto
    -0.14
    ÃŃc
    -0.14
    aws
    -0.14
    POSITIVE LOGITS
    .Arguments
    0.16
    éĥ
    0.14
    ertino
    0.14
    mans
    0.14
    ptune
    0.14
    :↵↵↵↵↵↵
    0.14
    odings
    0.14
    SCO
    0.13
    lescope
    0.13
     iso
    0.13
    Act Density 0.027%

    No Known Activations