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

    Neuronpedia

    INDEX
    Explanations

    mentions of measurement scales

    oai_token-act-pair · gpt-3.5-turbo

    references to measurement scales or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.87
    odge
    -0.80
    vous
    -0.75
    selves
    -0.72
    vironment
    -0.72
    ĪĴ
    -0.71
    unal
    -0.71
    uala
    -0.69
    utm
    -0.68
    aan
    -0.68
    POSITIVE LOGITS
     scale
    0.95
     scales
    0.82
     cooker
    0.75
     heights
    0.72
    enance
    0.71
    Factor
    0.70
     Scale
    0.70
     proportions
    0.69
     coffin
    0.69
     multiplier
    0.67
    Act Density 0.016%

    No Known Activations