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

    Neuronpedia

    INDEX
    Explanations

    _UNICODE characters representing symbols or expressions likely unrelated to the main content of text

    oai_token-act-pair · gpt-3.5-turbo

    patterns of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rake
    -0.77
    Downloadha
    -0.74
    ilater
    -0.72
    bda
    -0.68
    ministic
    -0.67
    illas
    -0.64
     forcefully
    -0.64
    lyak
    -0.63
    ierrez
    -0.63
    olves
    -0.63
    POSITIVE LOGITS
    ħ
    1.03
    Û
    0.92
    Ĥª
    0.87
    Į
    0.86
    ¬¼
    0.84
    к
    0.82
    ÑĤ
    0.81
    obar
    0.79
    İ
    0.78
    ŀ
    0.77
    Act Density 0.007%

    No Known Activations