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

    Neuronpedia

    INDEX
    Explanations

    code-related terminology and structure in programming or markup languages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.63
     κ
    -0.61
    erven
    -0.60
     ch
    -0.57
    ValueStyle
    -0.56
     inter
    -0.55
    (!_
    -0.52
     imp
    -0.51
     gra
    -0.50
     Ven
    -0.50
    POSITIVE LOGITS
    Personendaten
    1.03
     Houſe
    0.97
     purpoſe
    0.97
     Monfieur
    0.96
     itſelf
    0.91
     Jefus
    0.90
     "..\..\..\
    0.88
     pleaſure
    0.86
    Autoritní
    0.86
    ſelf
    0.85
    Act Density 0.003%

    No Known Activations