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

    Neuronpedia

    INDEX
    Explanations

    instances of measurements or quantities specified in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "about."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peaks
    -0.74
    chens
    -0.73
    Write
    -0.70
    Express
    -0.70
    NEY
    -0.65
    glas
    -0.65
    rift
    -0.63
     Shift
    -0.62
    ters
    -0.61
     Writ
    -0.61
    POSITIVE LOGITS
     halfway
    0.90
     midway
    0.78
    aleb
    0.77
    PsyNetMessage
    0.74
     dozen
    0.72
     Ambro
    0.72
     200
    0.72
    aimon
    0.72
     250
    0.70
    unin
    0.69
    Act Density 0.089%

    No Known Activations