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

    Neuronpedia

    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their contexts in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matic
    -0.80
    estine
    -0.78
    oard
    -0.75
    hood
    -0.74
    gotten
    -0.74
    MER
    -0.72
    aker
    -0.72
    stein
    -0.71
    pton
    -0.70
    ened
    -0.70
    POSITIVE LOGITS
    mph
    0.86
     ILCS
    0.85
     MPH
    0.84
     mph
    0.83
     pounds
    0.82
     chars
    0.82
    lbs
    0.80
     lbs
    0.79
     SHARES
    0.79
     kilograms
    0.78
    Act Density 0.048%

    No Known Activations