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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals with hyphenated last names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or identifiers associated with individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     operating
    -0.71
     elim
    -0.68
     NEXT
    -0.67
     sustaining
    -0.67
     rooting
    -0.67
     procedural
    -0.67
     procedure
    -0.64
     next
    -0.63
     susp
    -0.63
     acronym
    -0.63
    POSITIVE LOGITS
    Jones
    1.15
    sama
    1.12
    Smith
    1.06
    Williams
    1.04
    kun
    1.04
    vous
    1.03
    style
    1.03
    san
    1.03
    Wilson
    1.02
    chan
    1.01
    Act Density 0.028%

    No Known Activations