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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating accomplishment or observation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating processes and their accomplishments or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.65
    plates
    -0.59
    aneers
    -0.58
     arteries
    -0.58
     crus
    -0.57
    alions
    -0.57
    ologue
    -0.57
     plates
    -0.56
    ujah
    -0.55
    agon
    -0.54
    POSITIVE LOGITS
    SourceFile
    0.78
     explan
    0.71
    soType
    0.68
     borne
    0.65
    ECD
    0.64
    IER
    0.59
     however
    0.58
    UTC
    0.57
     anecd
    0.57
    ECA
    0.55
    Act Density 0.597%

    No Known Activations