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

    Neuronpedia

    INDEX
    Explanations

    date formats

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'O'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.82
    ãĥķ
    -0.77
     wip
    -0.74
    yards
    -0.70
    ÑĮ
    -0.70
     unfocusedRange
    -0.65
     PID
    -0.65
    ãĤ©
    -0.65
     à¨
    -0.64
    iard
    -0.63
    POSITIVE LOGITS
    lymp
    1.21
    tto
    1.17
    culus
    1.17
    vernight
    1.15
    ceans
    1.13
    scill
    1.07
    zzi
    1.03
    atmeal
    0.99
    rient
    0.97
    zzy
    0.96
    Act Density 0.027%

    No Known Activations