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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives or phrases indicating degree or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritel
    -0.17
    orus
    -0.16
    á½´
    -0.16
     вов
    -0.15
    urban
    -0.14
    initialized
    -0.14
     кеÑĢ
    -0.14
    alim
    -0.14
    tti
    -0.13
    _combo
    -0.13
    POSITIVE LOGITS
    èĨ
    0.15
    ucz
    0.15
    orp
    0.15
     Dag
    0.14
    xED
    0.14
    asionally
    0.13
    grily
    0.13
    Ctx
    0.13
     Cra
    0.13
    abra
    0.13
    Act Density 0.197%

    No Known Activations