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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical analysis and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yon
    -0.63
     Blackman
    -0.61
     Baran
    -0.60
     Mandel
    -0.58
     Mayfield
    -0.57
    RetentionPolicy
    -0.56
    δέ
    -0.56
    chol
    -0.56
    Groot
    -0.55
     hang
    -0.55
    POSITIVE LOGITS
     numerically
    1.20
    numerical
    1.16
     numerical
    1.15
     Numerical
    1.03
    ERICAL
    1.02
    Numerical
    1.01
     متعلقه
    0.96
    }")
    0.89
    ]');
    0.88
     quantitative
    0.86
    Act Density 0.167%

    No Known Activations