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

    Neuronpedia

    INDEX
    Explanations

    words that are highlighted with the character ' in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the apostrophe character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pru
    -0.66
    Ļ½
    -0.65
    rador
    -0.64
    manship
    -0.64
    İĭ
    -0.62
    ĻĤ
    -0.61
     ende
    -0.60
     answ
    -0.57
    »Ĵ
    -0.57
    acco
    -0.57
    POSITIVE LOGITS
    Cause
    0.92
    Allah
    0.83
    thur
    0.82
    Donnell
    0.72
    leys
    0.71
    S
    0.71
    Mech
    0.69
    eworks
    0.69
    Brien
    0.68
    ei
    0.68
    Act Density 0.049%

    No Known Activations