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

    Neuronpedia

    INDEX
    Explanations

    various references to books and downloadable content related to reading and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     correct
    -0.15
    dehy
    -0.14
     Harper
    -0.14
    омеÑĢ
    -0.14
    ysz
    -0.14
    DataExchange
    -0.14
    eÄį
    -0.14
    occo
    -0.14
    correct
    -0.14
    quier
    -0.13
    POSITIVE LOGITS
     Ever
    0.23
     ever
    0.22
    Ever
    0.21
    ow
    0.20
     overall
    0.20
    overall
    0.20
     EVER
    0.19
    -ever
    0.19
    ever
    0.18
     Overall
    0.18
    Act Density 0.093%

    No Known Activations