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

    Neuronpedia

    INDEX
    Explanations

    names or references to people

    oai_token-act-pair · gpt-3.5-turbo

    the word "ne" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -0.86
    ãĥ¼ãĥĨãĤ£
    -0.72
    Reviewer
    -0.72
    tailed
    -0.71
    rament
    -0.69
    displayText
    -0.67
    DOWN
    -0.66
    enhagen
    -0.66
    IAL
    -0.66
    ENCY
    -0.66
    POSITIVE LOGITS
    theless
    1.08
    arest
    1.01
    gan
    0.94
    volent
    0.93
    IGH
    0.88
    braska
    0.85
    cht
    0.85
    avy
    0.83
    farious
    0.83
    verend
    0.82
    Act Density 0.013%

    No Known Activations