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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in parentheses

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     everyday
    -0.80
     untreated
    -0.76
     deport
    -0.73
     wre
    -0.72
     imperson
    -0.71
     retard
    -0.71
     overpower
    -0.71
     intangible
    -0.71
     extingu
    -0.71
     mature
    -0.71
    POSITIVE LOGITS
    pictured
    1.36
    which
    1.34
    see
    1.34
    via
    1.30
    although
    1.25
    PDF
    1.24
    pdf
    1.24
    thanks
    1.22
    sic
    1.22
    http
    1.22
    Act Density 0.166%

    No Known Activations