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

    Neuronpedia

    INDEX
    Explanations

    specific information or details

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize specificity or particular details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Isles
    -0.79
    anon
    -0.71
    lyn
    -0.70
    ulton
    -0.67
    Progress
    -0.63
     Daily
    -0.62
     undoubtedly
    -0.62
     understandably
    -0.61
    izoph
    -0.60
    frog
    -0.60
    POSITIVE LOGITS
     targeted
    0.99
     tailored
    0.95
     exempted
    0.89
     targeting
    0.85
    atered
    0.80
     tuned
    0.79
     identifiable
    0.79
     designed
    0.78
     formulated
    0.78
    cedented
    0.78
    Act Density 0.020%

    No Known Activations