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

    Neuronpedia

    INDEX
    Explanations

    comments sections in texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    planes
    -0.73
    plane
    -0.71
    ously
    -0.67
    ALLY
    -0.66
    flies
    -0.66
    ment
    -0.66
    points
    -0.62
    lines
    -0.61
    aways
    -0.60
    lessness
    -0.60
    POSITIVE LOGITS
    ource
    1.09
    cript
    1.09
    poons
    1.08
    heet
    0.96
    ystem
    0.94
    ometimes
    0.94
    ensitive
    0.93
    uggest
    0.91
    ettings
    0.90
    ugar
    0.90
    Act Density 0.119%

    No Known Activations