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

    Neuronpedia

    INDEX
    Explanations

    references to letters being sent or written

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences of the word "letter", particularly in formal or official contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Races
    -0.75
    glers
    -0.74
     blink
    -0.72
    natureconservancy
    -0.71
    lap
    -0.70
    park
    -0.69
    variable
    -0.69
    hunt
    -0.69
    ource
    -0.68
    ahime
    -0.66
    POSITIVE LOGITS
    Dear
    1.12
     letter
    1.01
     correspondence
    0.99
     letters
    0.94
     dated
    0.93
     superiors
    0.88
     Letters
    0.85
     inbox
    0.84
    Letter
    0.83
     requesting
    0.82
    Act Density 0.227%

    No Known Activations