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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant quantities or intensities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of energy, resources, or emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.77
     proverb
    -0.71
    cknow
    -0.62
     Seas
    -0.61
    eming
    -0.59
     reopen
    -0.58
    pecially
    -0.57
     Rebell
    -0.57
     patron
    -0.57
    ocard
    -0.56
    POSITIVE LOGITS
     mileage
    0.86
     wasted
    0.86
    gain
    0.84
    fulness
    0.81
     variance
    0.79
    iness
    0.77
     flexibility
    0.77
     accumulated
    0.76
     overhead
    0.76
     variability
    0.76
    Act Density 0.268%

    No Known Activations