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

    Neuronpedia

    INDEX
    Explanations

    references to numbers with decimals

    oai_token-act-pair · gpt-3.5-turbo

    formatted citation references and page numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.77
     Aval
    -0.75
    idad
    -0.68
    stro
    -0.64
    bery
    -0.63
    holm
    -0.63
    DERR
    -0.63
    ependence
    -0.63
     Apostles
    -0.62
    emouth
    -0.62
    POSITIVE LOGITS
    rint
    1.12
    orter
    0.90
    amph
    0.80
    vl
    0.77
    fn
    0.75
     pg
    0.75
    Pg
    0.72
    lication
    0.72
    ierce
    0.72
    pg
    0.71
    Act Density 0.034%

    No Known Activations