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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names, particularly individuals and possibly entities or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogen
    -0.87
    nel
    -0.78
    anooga
    -0.78
    avage
    -0.77
    abeth
    -0.74
    ogens
    -0.73
    ifer
    -0.70
    win
    -0.69
    aton
    -0.69
    ellen
    -0.68
    POSITIVE LOGITS
    DragonMagazine
    1.05
    enance
    0.77
     salute
    0.71
    EStream
    0.67
    stanbul
    0.66
    ometimes
    0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.65
     resil
    0.65
    eco
    0.64
    ãĥ¯
    0.64
    Act Density 0.071%

    No Known Activations