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

    Neuronpedia

    INDEX
    Explanations

    structured mathematical or scientific notations and symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    mbre
    -0.60
     and
    -0.59
     plus
    -0.56
     same
    -0.55
    hra
    -0.53
    tigungs
    -0.53
     most
    -0.52
     no
    -0.51
     doGet
    -0.51
     while
    -0.50
    POSITIVE LOGITS
     Theſe
    0.89
     HasFactory
    0.88
     Jefus
    0.85
     Cæsar
    0.84
    SharedDtor
    0.81
    GenerationType
    0.77
     itſelf
    0.77
     Monfieur
    0.77
    ItemBackground
    0.77
    EDEFAULT
    0.76
    Act Density 0.021%

    No Known Activations