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

    Neuronpedia

    INDEX
    Explanations

    phrases describing someone's reputation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that establish reputation or characterization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.68
    raq
    -0.64
    omy
    -0.63
    ouls
    -0.63
    ousand
    -0.61
    ened
    -0.60
    mares
    -0.59
     enlarge
    -0.58
    profits
    -0.57
    Cause
    -0.57
    POSITIVE LOGITS
    pires
    1.03
     someone
    0.96
     an
    0.89
    someone
    0.87
     somebody
    0.85
     a
    0.85
    pired
    0.84
     savior
    0.84
     synonymous
    0.84
     fearless
    0.82
    Act Density 0.155%

    No Known Activations