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

    Neuronpedia

    INDEX
    Explanations

    references to the process of system startup or initialization

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     bootstrap
    -1.37
     bootstra
    -1.34
    bootstrap
    -1.20
     Bootstrap
    -1.18
    Bootstrap
    -1.11
     shoes
    -1.02
     Shoes
    -0.94
     SHOES
    -0.83
    Shoes
    -0.82
    ArrowToggle
    -0.82
    POSITIVE LOGITS
     boot
    1.59
     booted
    0.85
     booting
    0.84
     kick
    0.57
     lục
    0.52
     genomen
    0.51
     kicked
    0.50
    Bah
    0.50
     besides
    0.47
     mixed
    0.46
    Act Density 0.000%

    No Known Activations