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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating absence or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    каÑģ
    -0.17
    istrovstvÃŃ
    -0.15
    ÑĦоÑĢ
    -0.15
    neider
    -0.15
    edis
    -0.15
    å§
    -0.15
    rente
    -0.14
    riba
    -0.14
    typeof
    -0.14
     nÃło
    -0.14
    POSITIVE LOGITS
    ocker
    0.16
    ork
    0.16
    naments
    0.14
     Revel
    0.14
    retched
    0.14
    ãģ£ãģį
    0.13
    ock
    0.13
    碼
    0.13
    ascimento
    0.13
    ire
    0.13
    Act Density 0.067%

    No Known Activations