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

    Neuronpedia

    INDEX
    Explanations

    numerical data or structured formats involving quantitative information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    eqn
    -0.79
    RRect
    -0.77
     CCR
    -0.72
     kaka
    -0.70
     Corm
    -0.68
    CCR
    -0.67
    策
    -0.67
     Cornell
    -0.66
    GC
    -0.64
    izr
    -0.64
    POSITIVE LOGITS
     Shakspeare
    0.99
     vPvB
    0.98
     Hamid
    0.96
    berdayakan
    0.95
     myſelf
    0.95
     tdci
    0.90
    twimg
    0.89
     NDEBUG
    0.88
     tfsi
    0.87
    miary
    0.85
    Act Density 0.320%

    No Known Activations