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

    Neuronpedia

    INDEX
    Explanations

    exact descriptions or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concepts of similarity and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.74
    cest
    -0.63
    entimes
    -0.63
    amate
    -0.58
     underrated
    -0.58
    Pg
    -0.57
     trainer
    -0.57
    ways
    -0.57
    cade
    -0.57
     collections
    -0.57
    POSITIVE LOGITS
    irements
    0.82
    edIn
    0.79
    ACTION
    0.79
    Required
    0.71
    LOAD
    0.69
    Single
    0.68
    Ü
    0.68
    ORN
    0.65
    hov
    0.65
    ettings
    0.65
    Act Density 0.083%

    No Known Activations