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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "What does..."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    arters
    -0.75
     Islands
    -0.75
    boats
    -0.75
    agonists
    -0.74
    eers
    -0.73
    tracks
    -0.71
    bags
    -0.70
    fights
    -0.67
    runners
    -0.67
    boards
    -0.65
    POSITIVE LOGITS
    omething
    0.95
    berra
    0.89
    olation
    0.89
    hift
    0.84
    hip
    0.84
    hips
    0.82
    iosyncr
    0.78
    pace
    0.77
    onga
    0.76
    paces
    0.73
    Act Density 0.102%

    No Known Activations