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

    Neuronpedia

    INDEX
    Explanations

    numeric codes mixed with some text strings

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric sequences and data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceae
    -0.73
     cuts
    -0.64
    geries
    -0.61
     cosmetic
    -0.60
     necks
    -0.58
     bladder
    -0.58
     moderation
    -0.57
     differe
    -0.57
     hazards
    -0.57
     electors
    -0.56
    POSITIVE LOGITS
    tml
    0.81
    ĸļ
    0.81
    hyde
    0.78
    galitarian
    0.75
    SourceFile
    0.75
    vic
    0.73
     Citation
    0.70
    uk
    0.70
    cdn
    0.69
    IJ
    0.67
    Act Density 0.225%

    No Known Activations