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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating value judgment or assessment of worth

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote value or worth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.73
    pter
    -0.66
    cation
    -0.66
    DIT
    -0.65
    Lay
    -0.63
    BUS
    -0.63
     Blossom
    -0.61
     VIDEOS
    -0.60
    thumbnails
    -0.60
    Poly
    -0.60
    POSITIVE LOGITS
    iness
    0.97
     preserving
    0.93
     risking
    0.93
     mentioning
    0.92
    while
    0.91
     pursuing
    0.91
     remembering
    0.88
     trillions
    0.87
     celebrating
    0.87
    ily
    0.86
    Act Density 0.026%

    No Known Activations