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

    Neuronpedia

    INDEX
    Explanations

    technical language related to calculus and mathematical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duncan
    -0.17
     Downing
    -0.16
     Doll
    -0.16
     dam
    -0.15
     Dame
    -0.15
     Daddy
    -0.15
     dams
    -0.15
     Damien
    -0.14
     doll
    -0.14
    iry
    -0.14
    POSITIVE LOGITS
     Der
    0.93
    Der
    0.92
    der
    0.86
     der
    0.80
    _der
    0.78
     DER
    0.77
    .der
    0.77
     derivative
    0.76
    DER
    0.74
    deriv
    0.72
    Act Density 0.108%

    No Known Activations