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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases indicating a change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating transitions or transformations from one state to another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Differences
    -0.66
     Refresh
    -0.64
     Correction
    -0.60
     ¶
    -0.60
    awar
    -0.60
     rods
    -0.59
    Upgrade
    -0.59
     delay
    -0.57
     Improve
    -0.57
     Stories
    -0.56
    POSITIVE LOGITS
     downright
    1.02
    DonaldTrump
    0.83
     embracing
    0.83
     thriving
    0.79
     becoming
    0.77
     outright
    0.77
    fledged
    0.76
     embrace
    0.75
     fully
    0.74
     menacing
    0.73
    Act Density 0.326%

    No Known Activations