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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of people

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.69
     TAMADRA
    -0.58
    _-
    -0.57
    èª
    -0.57
    wcs
    -0.57
     Nadu
    -0.54
    ãĥģ
    -0.54
     ANGEL
    -0.54
    20439
    -0.54
    è£ħ
    -0.52
    POSITIVE LOGITS
    enhagen
    0.88
    xon
    0.72
    ricks
    0.65
    ulic
    0.63
    olin
    0.60
    apt
    0.60
    isch
    0.59
    arrass
    0.59
    anson
    0.58
    avier
    0.57
    Act Density 0.120%

    No Known Activations