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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deterioration or challenges increasing over time

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to progression and deterioration over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entirely
    -0.69
    ools
    -0.69
    oppers
    -0.69
    aido
    -0.67
     altogether
    -0.66
    ullivan
    -0.66
    kef
    -0.64
    zu
    -0.62
    shut
    -0.62
    zsche
    -0.60
    POSITIVE LOGITS
     progresses
    1.00
     progressively
    0.92
     increasing
    0.88
     repetition
    0.86
     increments
    0.86
     evolves
    0.85
     maturity
    0.84
     progressed
    0.84
     deeper
    0.83
     nearer
    0.83
    Act Density 0.382%

    No Known Activations