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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject "He"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pregn
    -0.66
     affiliate
    -0.62
     Gems
    -0.61
     guiActiveUnfocused
    -0.59
     Voltage
    -0.59
     Seym
    -0.58
     Observer
    -0.58
     CLR
    -0.58
     Punjab
    -0.57
     ASA
    -0.57
    POSITIVE LOGITS
    zbollah
    1.50
    resy
    1.31
    gemony
    1.25
    avier
    1.23
    aven
    1.21
    ldon
    1.13
    ather
    1.10
    pherd
    1.10
    reditary
    1.09
    brew
    1.09
    Act Density 0.171%

    No Known Activations