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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or entities written in all capital letters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ON."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ±
    -0.82
    Ĥª
    -0.73
    utenberg
    -0.72
    ãĤ§
    -0.70
    ãĤ©
    -0.69
    ãĥ¼ãĥ³
    -0.69
    ãĥĥ
    -0.68
     Wolfe
    -0.68
    ãĤ¶
    -0.67
    ãĤ¢ãĥ«
    -0.67
    POSITIVE LOGITS
    etheless
    1.19
    LY
    1.08
    ON
    1.03
    LINE
    0.98
    AUT
    0.94
    ONS
    0.86
    CE
    0.84
    ELY
    0.83
    IUM
    0.82
    ucle
    0.81
    Act Density 0.008%

    No Known Activations