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

    Neuronpedia

    INDEX
    Explanations

    statements emphasizing what is known or certain

    oai_token-act-pair · gpt-3.5-turbo

    phrases asserting knowledge or certainty about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pex
    -0.93
    ksh
    -0.75
    osi
    -0.73
    onies
    -0.70
    ermanent
    -0.70
    rentice
    -0.68
    cohol
    -0.68
    onial
    -0.65
    oling
    -0.64
    inance
    -0.64
    POSITIVE LOGITS
     ourselves
    0.92
     how
    0.85
     beforehand
    0.80
    ledged
    0.72
    ledge
    0.72
     anecd
    0.68
     guesses
    0.68
    lege
    0.68
    ETH
    0.68
     definitively
    0.67
    Act Density 0.092%

    No Known Activations