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

    Neuronpedia

    INDEX
    Explanations

    comparisons and references to alternatives or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.15
     instead
    -0.15
    inx
    -0.15
    cheid
    -0.15
    instead
    -0.14
    768
    -0.14
     gram
    -0.14
     Hel
    -0.14
    jang
    -0.14
    angan
    -0.14
    POSITIVE LOGITS
    uze
    0.17
    ıc
    0.16
    åĪ·
    0.15
    APER
    0.15
    /***/
    0.15
    peare
    0.15
    éra
    0.15
    than
    0.15
    PTS
    0.14
    peria
    0.14
    Act Density 0.137%

    No Known Activations