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

    Neuronpedia

    INDEX
    Explanations

    terms related to intelligence or skillfulness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intelligence or cleverness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atern
    -0.79
    units
    -0.67
     Garfield
    -0.65
     regress
    -0.64
    utation
    -0.63
     Ala
    -0.63
     unnecess
    -0.63
    pta
    -0.63
    atin
    -0.62
     Alive
    -0.62
    POSITIVE LOGITS
     savvy
    1.01
    erning
    0.78
     charm
    0.73
     brilliance
    0.72
     gull
    0.69
    ilant
    0.69
    flush
    0.69
     tricks
    0.69
     trick
    0.68
     impecc
    0.67
    Act Density 0.027%

    No Known Activations