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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific names or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.88
    mares
    -0.80
    upe
    -0.78
    arding
    -0.71
    ARD
    -0.71
    insula
    -0.69
    Ħ¢
    -0.67
    issance
    -0.66
    escription
    -0.65
    PDATE
    -0.64
    POSITIVE LOGITS
    tti
    0.90
    prime
    0.82
    tto
    0.82
    ations
    0.79
    tsky
    0.78
    tta
    0.78
    tex
    0.78
    stals
    0.78
    nesia
    0.76
    pheus
    0.74
    Act Density 1.489%

    No Known Activations