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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uniqueness or exclusivity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusivity or repetition, particularly focusing on the words "only" and "first."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omo
    -0.71
    wash
    -0.69
     dehyd
    -0.65
    aith
    -0.64
    mun
    -0.62
     Release
    -0.62
     RELEASE
    -0.61
     ABV
    -0.61
     Mage
    -0.60
    ithing
    -0.60
    POSITIVE LOGITS
    pmwiki
    0.83
     controversies
    0.76
     vex
    0.75
     accol
    0.73
     controversy
    0.73
     culprit
    0.72
     shenan
    0.69
     instances
    0.69
     sighting
    0.68
    ILLE
    0.67
    Act Density 0.050%

    No Known Activations