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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community and cooperation

    oai_token-act-pair · gpt-3.5-turbo

    symbols or notations that indicate varying levels of agreement or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vulner
    -0.74
     geared
    -0.74
     such
    -0.73
     QC
    -0.72
     spir
    -0.71
     suitable
    -0.69
     favour
    -0.69
     fab
    -0.67
     tasting
    -0.66
     mates
    -0.66
    POSITIVE LOGITS
    same
    1.39
    ultimate
    1.19
    latest
    1.15
    original
    1.15
    largest
    1.12
    official
    1.10
    highest
    1.09
    worst
    1.06
    ottest
    1.06
    majority
    1.05
    Act Density 0.104%

    No Known Activations