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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating warnings or disclaimers regarding sensitive content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptid
    -0.47
    (;;)
    -0.45
    IDENTITY
    -0.45
    ::$_
    -0.44
    LOV
    -0.43
    endgroup
    -0.42
     Scalars
    -0.42
    aryn
    -0.41
     graphql
    -0.41
     [+
    -0.41
    POSITIVE LOGITS
     chapter
    0.86
     chapters
    0.85
     Chapter
    0.81
     author
    0.78
     chapitre
    0.78
    Chapitre
    0.78
     story
    0.77
     fanfiction
    0.76
     fanfic
    0.76
    Chapter
    0.75
    Act Density 0.063%

    No Known Activations