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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Add" and phrases related to addition or accumulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ientôt
    -0.86
    picuous
    -0.61
     ویکی‌پدی
    -0.60
     Wikimedijinoj
    -0.57
    UrlResolution
    -0.55
    ([]
    -0.54
     masculinos
    -0.54
    .%
    -0.53
     AppModule
    -0.52
     incendie
    -0.52
    POSITIVE LOGITS
    IntoConstraints
    0.64
    Combine
    0.55
     Combine
    0.54
    TagHelper
    0.54
    再加上
    0.49
     كومونز
    0.47
     Cue
    0.46
     Coupled
    0.45
    영어
    0.44
     Combined
    0.44
    Act Density 0.204%

    No Known Activations