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

    Neuronpedia

    INDEX
    Explanations

    terms related to marathons and running

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mathematical concepts and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.74
    PLIC
    -0.73
    window
    -0.71
    ãĤŃ
    -0.68
    ãĤ«
    -0.68
    ========
    -0.67
     vac
    -0.66
    FILE
    -0.65
    ãĤ¦
    -0.65
    behind
    -0.65
    POSITIVE LOGITS
    yth
    1.56
    ythm
    1.15
    yss
    1.01
    urst
    0.91
    opter
    0.91
    imer
    0.90
    anson
    0.90
    alon
    0.89
    rones
    0.87
    luaj
    0.86
    Act Density 0.009%

    No Known Activations