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

    Neuronpedia

    INDEX
    Explanations

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    symbols indicating a URL or web address

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boards
    -0.72
    ruits
    -0.71
    egg
    -0.71
    =/
    -0.71
    ternity
    -0.70
    redits
    -0.69
    mond
    -0.68
    arag
    -0.66
    -+-+
    -0.65
    ments
    -0.64
    POSITIVE LOGITS
    stress
    0.70
     Galile
    0.68
    ificent
    0.64
    foreseen
    0.63
    interrupted
    0.63
     fractured
    0.61
     congr
    0.60
     sized
    0.60
     deed
    0.59
     dos
    0.58
    Act Density 0.000%

    No Known Activations