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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions indicating quantity or quality

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

    a followed by positive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magnétique
    -0.51
    garek
    -0.45
    randomUUID
    -0.43
     poiché
    -0.43
    wnątrz
    -0.42
     względu
    -0.42
     alguém
    -0.41
     aanzien
    -0.41
     Leidenschaft
    -0.41
     Gegenwart
    -0.41
    POSITIVE LOGITS
     Done
    0.90
     done
    0.88
     DONE
    0.83
    doing
    0.78
    Done
    0.76
    done
    0.76
    SharedDtor
    0.75
    AddTagHelper
    0.75
     Doing
    0.74
    Doing
    0.73
    Act Density 0.017%

    No Known Activations