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

    Neuronpedia

    INDEX
    Explanations

    first-person statements indicating state or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĵ
    -0.17
     nuest
    -0.15
    cona
    -0.15
     itself
    -0.14
    ERGE
    -0.14
    -FIRST
    -0.14
    obao
    -0.14
     addCriterion
    -0.14
    inis
    -0.14
    loub
    -0.14
    POSITIVE LOGITS
     myself
    0.30
     sure
    0.29
    aze
    0.24
     sorry
    0.22
     Sure
    0.21
     hereby
    0.21
    Sure
    0.20
     guessing
    0.19
     not
    0.19
     privileged
    0.18
    Act Density 0.145%

    No Known Activations