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

    Neuronpedia

    INDEX
    Explanations

    percentages or related numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to percentages or statistical certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.89
    zie
    -0.85
    sels
    -0.72
    åĤ
    -0.72
    hap
    -0.69
    ipples
    -0.68
    */(
    -0.67
    EStream
    -0.67
    isure
    -0.67
     Skies
    -0.66
    POSITIVE LOGITS
     Invisible
    0.79
     certainty
    0.77
    heartedly
    0.73
     ethanol
    0.72
     pure
    0.70
     accurate
    0.69
     satisfaction
    0.68
     humidity
    0.66
     True
    0.64
     assured
    0.64
    Act Density 0.048%

    No Known Activations