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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rights and permissions regarding intellectual property, particularly concerning the use of names and likenesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.89
    Espèce
    -0.79
    MessageTagHelper
    -0.73
     pleaſure
    -0.73
    uxxxx
    -0.72
     Walkover
    -0.70
     Jefus
    -0.70
    ſelf
    -0.69
     myſelf
    -0.69
     оригіналу
    -0.69
    POSITIVE LOGITS
     to
    0.49
     her
    0.44
     into
    0.43
     man
    0.43
    ,
    0.40
     inf
    0.40
    ...
    0.39
     as
    0.39
     for
    0.39
    ent
    0.38
    Act Density 0.803%

    No Known Activations