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

    Neuronpedia

    INDEX
    Explanations

    references to chapters and numerical ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tunggal
    -0.61
    horabuena
    -0.50
     glú
    -0.48
     verkau
    -0.47
     alimentaria
    -0.47
     mutlu
    -0.47
     muerta
    -0.47
    destroyAll
    -0.46
     poffible
    -0.46
    ArrowToggle
    -0.46
    POSITIVE LOGITS
     effect
    0.67
     chapter
    0.65
     Chapters
    0.64
     chase
    0.61
     Chapter
    0.59
     mercy
    0.57
     chap
    0.57
    Chapters
    0.56
     Chap
    0.56
     genre
    0.55
    Act Density 0.298%

    No Known Activations