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

    Neuronpedia

    INDEX
    Explanations

    references to cryptographic concepts and functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    KURZBESCHREIBUNG
    -0.92
    afficheront
    -0.85
     يتيمه
    -0.85
    ConstraintMaker
    -0.84
     lenker
    -0.79
    Hentet
    -0.78
    tvguidetime
    -0.75
    reportWebVitals
    -0.74
    Diwedd
    -0.74
    !*\
    -0.71
    POSITIVE LOGITS
    робнее
    0.48
    addGap
    0.45
    Cau
    0.43
     denk
    0.43
    CDATA
    0.43
    iformis
    0.43
    TRES
    0.41
    Buk
    0.40
    ͘
    0.40
     Kri
    0.40
    Act Density 0.077%

    No Known Activations