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

    Neuronpedia

    INDEX
    Explanations

    text related to official correspondence or communication in written form

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "letter" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rans
    -0.68
    oken
    -0.67
    orsi
    -0.66
     Tune
    -0.63
    tics
    -0.62
     Abel
    -0.61
    oleon
    -0.61
     Occupations
    -0.61
     Nex
    -0.60
    illon
    -0.60
    POSITIVE LOGITS
     letter
    0.98
    Letter
    0.94
     inbox
    0.91
    velop
    0.90
    letter
    0.88
     letters
    0.85
    press
    0.82
    boxing
    0.81
     penned
    0.80
    worms
    0.79
    Act Density 0.025%

    No Known Activations