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

    Neuronpedia

    INDEX
    Explanations

    quotations or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases containing a period at the end

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.73
    urer
    -0.70
     facult
    -0.70
    illet
    -0.69
     unex
    -0.68
     mosqu
    -0.66
    rogens
    -0.66
     metic
    -0.66
    arer
    -0.65
    cha
    -0.65
    POSITIVE LOGITS
     Asked
    0.89
     Meanwhile
    0.85
    /"
    0.83
     Nevertheless
    0.82
     Apparently
    0.81
     According
    0.80
     Accordingly
    0.79
    tumblr
    0.79
    Attempts
    0.78
     Additionally
    0.77
    Act Density 0.086%

    No Known Activations