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

    Neuronpedia

    INDEX
    Explanations

    predictions or future intentions expressed through the word "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ling
    -0.15
    esser
    -0.14
    ement
    -0.14
     land
    -0.14
    emotion
    -0.14
    ystone
    -0.14
    illo
    -0.14
    land
    -0.14
    ements
    -0.13
    cobra
    -0.13
    POSITIVE LOGITS
    weis
    0.15
    etÃŃ
    0.14
    &page
    0.14
    renom
    0.14
    egov
    0.14
    ominator
    0.14
    .IContainer
    0.14
    zig
    0.13
    -variable
    0.13
    agu
    0.13
    Act Density 0.050%

    No Known Activations