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

    Neuronpedia

    INDEX
    Explanations

    written statements or quotes by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wrote."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.76
    Ĭ±
    -0.74
    eger
    -0.72
    ackle
    -0.72
     ILCS
    -0.71
    nel
    -0.66
    icons
    -0.66
    illon
    -0.66
    Unity
    -0.64
    angular
    -0.64
    POSITIVE LOGITS
    smanship
    0.84
     penned
    0.82
    ipel
    0.75
     notebook
    0.75
     memos
    0.74
     poems
    0.74
     letters
    0.73
     journal
    0.72
     essays
    0.71
    wrote
    0.70
    Act Density 0.034%

    No Known Activations