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

    Neuronpedia

    INDEX
    Explanations

    names of well-known individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly of individuals and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.81
     TAMADRA
    -0.71
     boosters
    -0.60
    bilt
    -0.60
    ModLoader
    -0.59
    Interstitial
    -0.58
     Bee
    -0.58
    natureconservancy
    -0.57
     hereafter
    -0.57
    Ĥİ
    -0.57
    POSITIVE LOGITS
    enhagen
    0.96
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.78
    umeric
    0.75
    restrial
    0.69
    heed
    0.66
    nih
    0.64
    è¦ļéĨĴ
    0.63
    ensed
    0.62
    chnology
    0.62
    itte
    0.61
    Act Density 0.434%

    No Known Activations