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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in the context of official statements or reports

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically personal names and titles within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.95
    tumblr
    -0.69
     sidx
    -0.68
     mischief
    -0.67
     snowball
    -0.67
     womb
    -0.65
    gettable
    -0.64
     careers
    -0.63
    VALUE
    -0.63
     menstru
    -0.62
    POSITIVE LOGITS
     Garrett
    0.86
     Vance
    0.86
     Walsh
    0.82
     Bennett
    0.81
     Dillon
    0.79
     Hogan
    0.77
     Brooks
    0.77
     Ion
    0.77
     Thompson
    0.76
     Grant
    0.76
    Act Density 0.204%

    No Known Activations