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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of usual or normal occurrences

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as usual"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Stars
    -0.85
     Starship
    -0.79
    lez
    -0.79
    sten
    -0.78
    kamp
    -0.76
    mented
    -0.75
    zik
    -0.73
    robe
    -0.71
    port
    -0.70
    STAR
    -0.70
    POSITIVE LOGITS
     suspects
    0.92
     disclaim
    0.88
     disclaimer
    0.82
     deviations
    0.80
     assortment
    0.79
     caveats
    0.77
     mosqu
    0.77
     defences
    0.76
     occurrences
    0.74
    tenance
    0.74
    Act Density 0.015%

    No Known Activations