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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific entities or organizations identified as "En" with varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "En" or related variations, indicating a focus on specific organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.77
     Heights
    -0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.72
    ij士
    -0.70
    UGH
    -0.68
     Palmer
    -0.68
    sburgh
    -0.67
     Parables
    -0.65
     Dare
    -0.65
    hyde
    -0.63
    POSITIVE LOGITS
    viron
    1.27
    emy
    1.09
    chanted
    1.07
    forcer
    1.07
    rollment
    1.06
    zyme
    1.04
    riched
    1.02
    raged
    1.02
    cyclop
    1.02
    closure
    1.01
    Act Density 0.015%

    No Known Activations