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

    Neuronpedia

    INDEX
    Explanations

    references to library resources and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     w
    -0.16
    ema
    -0.16
    156
    -0.15
     p
    -0.15
     Pax
    -0.14
     Yard
    -0.14
    869
    -0.14
    ková
    -0.14
     that
    -0.14
    ignon
    -0.14
    POSITIVE LOGITS
    ymax
    0.17
    alars
    0.17
    illage
    0.16
    uste
    0.16
    γγ
    0.16
    Tween
    0.16
    adelphia
    0.15
    cdecl
    0.15
    opher
    0.15
    orex
    0.15
    Act Density 0.007%

    No Known Activations