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

    Neuronpedia

    INDEX
    Explanations

    the word "more" in varying contexts

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

    degree of comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.68
     disambiguazione
    -0.65
    kháu
    -0.64
    MigrationBuilder
    -0.57
     Connectez
    -0.53
    RenderAtEndOf
    -0.53
    rungsseite
    -0.49
     springfox
    -0.48
     بيها
    -0.48
     kasarigan
    -0.48
    POSITIVE LOGITS
     MUCH
    0.56
     very
    0.55
     VERY
    0.53
     extremely
    0.52
     Very
    0.51
     enormously
    0.51
    훨
    0.51
     Muito
    0.50
     tremendously
    0.49
     extrêmement
    0.48
    Act Density 0.012%

    No Known Activations