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

    Neuronpedia

    INDEX
    Explanations

    conjunctions used to contrast or add information

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases and conjunctions that convey contrast or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.84
    ickets
    -0.81
     intervals
    -0.74
    itivity
    -0.73
    imation
    -0.73
    gency
    -0.72
    imize
    -0.72
    ision
    -0.72
    imum
    -0.71
    icals
    -0.70
    POSITIVE LOGITS
     obsessed
    1.30
     incapable
    1.30
     proud
    1.26
     inexperienced
    1.24
     prone
    1.23
     fluent
    1.23
     wiser
    1.21
     proficient
    1.20
     addicted
    1.20
     capable
    1.20
    Act Density 0.331%

    No Known Activations