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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     portfolios
    -0.71
    è¦ļéĨĴ
    -0.63
    Downloadha
    -0.61
     sentiments
    -0.61
    Footnote
    -0.61
     qualities
    -0.61
     surveillance
    -0.61
     flora
    -0.59
    SourceFile
    -0.59
     portfolio
    -0.58
    POSITIVE LOGITS
    here
    0.81
    asus
    0.81
    adays
    0.80
    hew
    0.76
     begs
    0.72
    wu
    0.68
    ciating
    0.68
     THERE
    0.67
    hops
    0.65
    rade
    0.65
    Act Density 0.128%

    No Known Activations