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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the start of a new section or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ','.
    -0.61
    голь
    -0.60
    seteq
    -0.60
     empre
    -0.60
     ?>/
    -0.59
    bürgermeister
    -0.58
    ://"
    -0.58
     "
    -0.58
    !="
    -0.55
    zyl
    -0.55
    POSITIVE LOGITS
     Majefty
    1.23
    ſelf
    1.21
     itſelf
    1.20
     Anſ
    1.15
    ſelves
    1.14
     Reſ
    1.12
     ſta
    1.09
     myſelf
    1.09
     Jefus
    1.08
     faſt
    1.08
    Act Density 0.040%

    No Known Activations