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

    Neuronpedia

    INDEX
    Explanations

    references to first occurrences or pioneering achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OrBuilder
    -0.83
    ArrowToggle
    -0.78
     Administrativna
    -0.76
    PhysRevD
    -0.75
    Various
    -0.75
    various
    -0.73
     tantôt
    -0.72
     InputDecoration
    -0.72
     ſeveral
    -0.71
     îna
    -0.71
    POSITIVE LOGITS
     ever
    0.92
     truly
    0.90
     réellement
    0.87
     publicly
    0.85
     fully
    0.83
     überhaupt
    0.81
     véritable
    0.80
     formally
    0.80
     officially
    0.78
     vraiment
    0.74
    Act Density 0.339%

    No Known Activations