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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating availability or access

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avra
    -0.15
    кÑĥÑĤ
    -0.15
    yor
    -0.14
    iasi
    -0.14
     Stark
    -0.14
    eÄį
    -0.13
    erer
    -0.13
     ç¦
    -0.13
    resents
    -0.13
    оÑĢаз
    -0.13
    POSITIVE LOGITS
    &action
    0.16
     action
    0.16
    reh
    0.14
    ANDING
    0.14
    amma
    0.14
    CED
    0.14
    ราà¸Ĭ
    0.14
    WARDED
    0.13
    940
    0.13
     Äijá»Ŀi
    0.13
    Act Density 0.073%

    No Known Activations