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

    Neuronpedia

    INDEX
    Explanations

    references to various highly specific robot or weapon arrangements and configurations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    enderror
    -0.63
    moso
    -0.56
     Franz
    -0.56
    uze
    -0.54
    MessageTagHelper
    -0.53
    __':
    -0.52
    Franz
    -0.52
     ASN
    -0.52
    ghis
    -0.51
    finalize
    -0.50
    POSITIVE LOGITS
     Ry
    3.27
    Ry
    2.84
     ry
    1.80
     RY
    1.80
     Ryder
    1.12
     Ryu
    0.96
     Ryd
    0.79
     Ры
    0.78
    Ryu
    0.73
     Ryo
    0.73
    Act Density 0.002%

    No Known Activations