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

    Neuronpedia

    INDEX
    Explanations

    information related to statistical margins of error

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statistical margins of error

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wives
    -0.84
    è¦ļéĨĴ
    -0.81
     Reloaded
    -0.77
    wife
    -0.74
    orer
    -0.74
    soDeliveryDate
    -0.72
    xual
    -0.68
    itions
    -0.68
    heid
    -0.68
    marked
    -0.66
    POSITIVE LOGITS
     maturity
    0.83
     parity
    0.78
     separation
    0.76
     accomplishment
    0.75
     computation
    0.74
     disbelief
    0.72
     communication
    0.71
     contention
    0.71
     competence
    0.70
     gain
    0.68
    Act Density 0.108%

    No Known Activations