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

    Neuronpedia

    INDEX
    Explanations

    terms related to nonlinearity in mathematical or physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NonNull
    -0.17
    allon
    -0.16
     nonzero
    -0.15
     Hoff
    -0.15
    _NON
    -0.15
    ovich
    -0.14
     VIP
    -0.14
    utton
    -0.14
     Indo
    -0.14
    834
    -0.14
    POSITIVE LOGITS
    line
    0.21
    tr
    0.20
     trivial
    0.20
    liner
    0.18
    antic
    0.18
    van
    0.18
    lien
    0.17
    compact
    0.17
    -zero
    0.17
    llen
    0.17
    Act Density 0.016%

    No Known Activations