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

    Neuronpedia

    INDEX
    Explanations

    the phrase "Too Close"

    oai_token-act-pair · gpt-3.5-turbo

    specific titles or phrases that indicate proximity or closeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Independence
    -0.68
     Commentary
    -0.67
    crow
    -0.66
    cept
    -0.65
     Compass
    -0.63
    ahu
    -0.63
    rast
    -0.62
    respond
    -0.62
    draw
    -0.61
     Clarkson
    -0.61
    POSITIVE LOGITS
    chwitz
    0.79
    vid
    0.68
     ribbon
    0.67
     sshd
    0.66
    iped
    0.65
    uilt
    0.65
    aird
    0.63
    anski
    0.62
    etsy
    0.62
     DOS
    0.62
    Act Density 0.000%

    No Known Activations