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

    Neuronpedia

    INDEX
    Explanations

    references to paper and paper-related products or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yar
    -0.17
    yu
    -0.17
    y
    -0.17
    yah
    -0.16
    ãģ¦
    -0.16
    åĢĻ
    -0.16
    ot
    -0.16
    sic
    -0.16
    s
    -0.15
    yw
    -0.15
    POSITIVE LOGITS
    -paper
    0.19
    theid
    0.17
    clip
    0.16
    iž
    0.16
    ELLOW
    0.16
    stown
    0.16
    oleÄį
    0.16
    edly
    0.16
     Cust
    0.15
    mia
    0.15
    Act Density 0.029%

    No Known Activations