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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recognition and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nila
    -0.14
    (Paint
    -0.14
    istrovstvÃŃ
    -0.13
    overall
    -0.13
     hind
    -0.13
     indeed
    -0.13
     probs
    -0.13
    _Api
    -0.13
     déjÃł
    -0.13
    à¥ģà¤Ĩ
    -0.13
    POSITIVE LOGITS
     optionally
    0.23
     (~
    0.19
     embar
    0.17
    utton
    0.17
    (*)
    0.16
     ~=
    0.16
     FIXME
    0.16
    (~
    0.15
     dialogs
    0.15
     TBD
    0.14
    Act Density 0.045%

    No Known Activations