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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Month.Day" within text

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain periods, indicating sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cradle
    -0.69
    atories
    -0.65
     clut
    -0.65
     outstanding
    -0.65
     intangible
    -0.64
    wered
    -0.64
     chimpanzees
    -0.62
    anium
    -0.62
     intellectual
    -0.61
     achievements
    -0.61
    POSITIVE LOGITS
    Downloadha
    0.85
     Madness
    0.85
    Pacific
    0.77
    luaj
    0.74
     Macedonia
    0.73
     Accessed
    0.72
    sbm
    0.70
     Fool
    0.70
     Higgins
    0.69
    grad
    0.68
    Act Density 0.047%

    No Known Activations