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

    Neuronpedia

    INDEX
    Explanations

    tokens associated with significant actions or concepts related to events or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Howe
    -0.15
     behalf
    -0.15
    ilim
    -0.14
    ÑĦÑĤ
    -0.14
    jian
    -0.14
    jon
    -0.14
    ertos
    -0.14
    103
    -0.14
    .school
    -0.14
    etting
    -0.13
    POSITIVE LOGITS
     اÙĦÙĪص
    0.15
    aul
    0.15
    ensa
    0.15
     Hedge
    0.15
     ÑĢев
    0.15
    uer
    0.14
    noun
    0.14
    /extensions
    0.14
    eeper
    0.14
    .ng
    0.14
    Act Density 0.001%

    No Known Activations