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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities, specifically focusing on the last names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific surnames or individuals' names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨ
    -0.83
    士
    -0.82
    ãĤ¼ãĤ¦ãĤ¹
    -0.82
    ãĤ½
    -0.79
    é¾įåĸļ士
    -0.75
     [|
    -0.73
    ISH
    -0.73
     ILCS
    -0.72
    mental
    -0.70
    EED
    -0.70
    POSITIVE LOGITS
    lyak
    0.93
     Pes
    0.92
    berman
    0.87
    achy
    0.84
    kens
    0.83
    ollah
    0.83
    waters
    0.78
    ablishment
    0.77
    gom
    0.77
    ky
    0.76
    Act Density 0.013%

    No Known Activations