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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that end with a period followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    instances of statistical claims or statements about events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.96
     metic
    -0.77
     charism
    -0.73
     derog
    -0.72
     emot
    -0.69
    bryce
    -0.69
     perspect
    -0.68
     skelet
    -0.68
     simultane
    -0.67
     princ
    -0.67
    POSITIVE LOGITS
     Months
    0.93
    Thousands
    0.92
    Yet
    0.89
     But
    0.88
     Thousands
    0.88
     Instead
    0.88
    But
    0.87
    ↵
    0.87
    Few
    0.86
     Newly
    0.85
    Act Density 0.216%

    No Known Activations