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

    Neuronpedia

    INDEX
    Explanations

    contextual references to quantities or presence in relation to actions and subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxt
    -0.17
    Exited
    -0.17
    alama
    -0.16
    GenerationStrategy
    -0.16
    اÙĪرÛĮ
    -0.15
    uto
    -0.15
    ucz
    -0.15
    anou
    -0.15
    icÃŃ
    -0.15
    ideos
    -0.15
    POSITIVE LOGITS
    ivi
    0.18
    ims
    0.15
    ston
    0.14
    ãĥ³ãĥģ
    0.14
     g
    0.14
    bara
    0.14
     Eigen
    0.14
     ret
    0.14
    WARE
    0.14
    fish
    0.14
    Act Density 0.012%

    No Known Activations