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

    Neuronpedia

    INDEX
    Explanations

    short words that seem to be placeholders or errors in the text, possibly arising from encoding issues

    oai_token-act-pair · gpt-3.5-turbo

    negated forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.86
     SetTextColor
    -0.71
    CVE
    -0.68
     Flavoring
    -0.66
     Gleaming
    -0.63
     Radiation
    -0.63
    Intern
    -0.62
    £ı
    -0.61
     Variant
    -0.60
    soType
    -0.60
    POSITIVE LOGITS
    unes
    1.02
    cha
    0.95
    weet
    0.92
    une
    0.90
    otally
    0.89
    itled
    0.89
    ruck
    0.89
    ucked
    0.89
    aper
    0.88
    actic
    0.87
    Act Density 0.066%

    No Known Activations