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

    Neuronpedia

    INDEX
    Explanations

    references to religious or biblical objects, practices, or concepts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     suspect
    -0.59
    rani
    -0.58
     Rial
    -0.56
    Vain
    -0.56
    Amm
    -0.55
    ivor
    -0.54
     Duda
    -0.54
    Wy
    -0.53
    季
    -0.53
     dép
    -0.52
    POSITIVE LOGITS
     forehead
    1.47
    amus
    1.06
    atri
    0.97
     Marty
    0.90
     extrapolated
    0.82
     extrapolation
    0.81
    kloped
    0.81
    Marty
    0.79
     martyr
    0.73
     Todd
    0.70
    Act Density 0.003%

    No Known Activations