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

    Neuronpedia

    INDEX
    Explanations

    phrases related to categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aÄį
    -0.15
    alara
    -0.15
    _misc
    -0.14
    elocity
    -0.14
    atar
    -0.13
    isco
    -0.13
    ÏĨα
    -0.13
    vang
    -0.13
    ulario
    -0.13
    resolver
    -0.13
    POSITIVE LOGITS
     whereas
    0.23
     Whereas
    0.21
    optim
    0.16
    rax
    0.15
    auce
    0.15
     Tome
    0.15
     ÙĨع
    0.14
     optim
    0.14
     èĢĮ
    0.14
     Ston
    0.14
    Act Density 0.343%

    No Known Activations