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

    Neuronpedia

    INDEX
    Explanations

    assessments of character or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     probably
    -0.18
    aida
    -0.17
     presumably
    -0.17
     Probably
    -0.16
    croft
    -0.16
     supposedly
    -0.15
    probably
    -0.15
    Probably
    -0.15
    Ỽ
    -0.14
    ï¸
    -0.14
    POSITIVE LOGITS
    -random
    0.16
    ATUS
    0.15
     endless
    0.15
    lopen
    0.15
     intent
    0.14
     quite
    0.14
     ÙģÙĤد
    0.14
    æį·
    0.14
     forgotten
    0.14
    *)_
    0.14
    Act Density 0.090%

    No Known Activations