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

    Neuronpedia

    INDEX
    Explanations

    references to commissioners and institutions in a governmental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uses
    -0.43
    ass
    -0.43
     Cer
    -0.43
     a
    -0.42
     Ger
    -0.41
     S
    -0.41
    doi
    -0.41
     Kil
    -0.41
     Eg
    -0.40
     He
    -0.40
    POSITIVE LOGITS
     itſelf
    1.03
    ſelf
    0.96
     faſt
    0.94
     myſelf
    0.94
     pleaſure
    0.90
     ſche
    0.86
     poffible
    0.82
     purpoſe
    0.82
     houſe
    0.81
    ſelves
    0.81
    Act Density 0.251%

    No Known Activations