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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing "better than" constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing comparisons of size or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparative X than Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    andle
    -0.54
    比べると
    -0.53
    Diweddarwch
    -0.52
     Wikiseite
    -0.52
     main
    -0.51
    Composable
    -0.49
    cstdlib
    -0.48
    raszamy
    -0.47
    otella
    -0.45
    न्दर्भ
    -0.44
    POSITIVE LOGITS
     anything
    1.33
     any
    1.15
    anything
    1.14
    Anything
    1.07
     Anything
    1.07
     ANYTHING
    1.04
     anyone
    1.00
    任何
    0.95
     qualquer
    0.94
     cualquier
    0.90
    Act Density 0.068%

    No Known Activations