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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical rates and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rn
    -0.18
    ness
    -0.18
    Ùĩ
    -0.16
    imon
    -0.15
    ner
    -0.15
    ie
    -0.15
    rk
    -0.14
    ry
    -0.14
    mer
    -0.14
    awy
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.18
    upertino
    0.16
    ully
    0.15
    еÑĢап
    0.15
    rophic
    0.15
    aru
    0.15
    payer
    0.15
    tsky
    0.15
    ngr
    0.14
    MM
    0.14
    Act Density 0.043%

    No Known Activations