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

    Neuronpedia

    INDEX
    Explanations

    elements related to narrative structure and character development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INCREMENT
    -0.15
    rada
    -0.14
    tuk
    -0.14
    ovit
    -0.14
     travail
    -0.13
    ÄĽle
    -0.13
    499
    -0.13
     Kok
    -0.13
    500
    -0.13
    496
    -0.13
    POSITIVE LOGITS
     sometimes
    0.16
    ometimes
    0.16
    uerdo
    0.15
     often
    0.15
     Grat
    0.14
    ems
    0.14
    ron
    0.14
    idla
    0.14
    omb
    0.14
     events
    0.14
    Act Density 0.121%

    No Known Activations