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

    Neuronpedia

    INDEX
    Explanations

    language related to legal or financial obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.35
     houſe
    -1.28
     purpoſe
    -1.27
     Majefty
    -1.26
     Monfieur
    -1.21
     myſelf
    -1.20
     faſt
    -1.16
     Houſe
    -1.14
     ſche
    -1.13
     Jefus
    -1.13
    POSITIVE LOGITS
     human
    0.44
     de
    0.43
     no
    0.42
     so
    0.41
     pe
    0.41
     some
    0.38
    Edited
    0.38
     perhaps
    0.38
     [
    0.38
     un
    0.38
    Act Density 2.771%

    No Known Activations