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

    Neuronpedia

    INDEX
    Explanations

    self-reflective or persuasive language

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to self-persuasion and convincing others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.85
     largeDownload
    -0.63
     replaced
    -0.61
     Gutenberg
    -0.59
     blat
    -0.58
     charism
    -0.58
     strides
    -0.58
    tackle
    -0.56
     ILCS
    -0.56
    itars
    -0.55
    POSITIVE LOGITS
    selves
    0.88
    antics
    0.84
    DERR
    0.79
     skeptical
    0.75
    oppers
    0.71
    ynes
    0.71
     gull
    0.70
    hematically
    0.67
    jah
    0.67
    urers
    0.66
    Act Density 0.319%

    No Known Activations