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

    Neuronpedia

    INDEX
    Explanations

    currency symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols used for emphasis or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crusher
    -0.80
    WARD
    -0.77
    swick
    -0.73
     Nikon
    -0.72
     Widow
    -0.71
     Tid
    -0.68
    ãģ®éŃĶ
    -0.68
    wagen
    -0.67
     Bond
    -0.67
     Shed
    -0.63
    POSITIVE LOGITS
    Ħ¢
    1.41
    ł
    1.28
    ĵ
    1.22
    Ĥ
    1.20
    Ħ
    1.19
    ŀ
    1.19
    Ĥª
    1.17
    ķ
    1.16
    ĩ
    1.13
    ļ
    1.12
    Act Density 0.005%

    No Known Activations