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

    Neuronpedia

    INDEX
    Explanations

    physical attributes and characteristics of objects

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives and verbs related to physical attributes and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivals
    -0.88
     Taxes
    -0.85
    inav
    -0.84
    benef
    -0.78
     Calls
    -0.78
     Publishers
    -0.75
     Opportun
    -0.73
    ossom
    -0.73
     Ranking
    -0.72
     Debate
    -0.71
    POSITIVE LOGITS
     coated
    1.16
     adorned
    1.13
     glued
    1.10
     replaced
    1.09
     decorated
    1.09
     removable
    1.08
     fitted
    1.07
     removed
    1.07
     molded
    1.06
     thinner
    1.06
    Act Density 0.236%

    No Known Activations