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

    Neuronpedia

    INDEX
    Explanations

    comparisons using similes, often involving feelings or emotions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparisons or similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omen
    -0.75
    externalActionCode
    -0.72
    PsyNetMessage
    -0.67
    ulic
    -0.65
    Recommend
    -0.63
    ertain
    -0.61
    byn
    -0.61
     unden
    -0.61
    SourceFile
    -0.61
    conservancy
    -0.60
    POSITIVE LOGITS
     crap
    1.17
     shit
    1.08
    lier
    0.95
     idiots
    0.91
    liest
    0.87
     fools
    0.81
     somebody
    0.78
     they
    0.76
     someone
    0.76
     gods
    0.74
    Act Density 0.048%

    No Known Activations