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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retard
    -0.84
     clin
    -0.84
     increment
    -0.82
     administration
    -0.72
     diving
    -0.71
     uncons
    -0.71
     accrued
    -0.71
     electr
    -0.70
     bunker
    -0.70
     tear
    -0.70
    POSITIVE LOGITS
    sic
    1.80
    formerly
    1.60
    which
    1.49
    aka
    1.48
    pron
    1.47
    pictured
    1.47
    meaning
    1.39
    see
    1.38
    later
    1.37
    whose
    1.37
    Act Density 0.146%

    No Known Activations