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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vla
    -0.16
     Sterling
    -0.15
    thal
    -0.15
    antidad
    -0.14
    enal
    -0.14
    oland
    -0.14
    rough
    -0.14
    bold
    -0.14
     Moran
    -0.14
    cheme
    -0.14
    POSITIVE LOGITS
    baugh
    0.16
     affairs
    0.15
    ogr
    0.15
    ìĹ°
    0.15
     orth
    0.14
     publicly
    0.14
    oji
    0.14
    udur
    0.14
     vÃŃde
    0.14
    _beam
    0.13
    Act Density 0.007%

    No Known Activations