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

    Neuronpedia

    INDEX
    Explanations

    imperatives and suggestions related to actions or considerations

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

    should + action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.36
    bcryptjs
    -0.35
    astify
    -0.35
    astéroïdes
    -0.33
    tronlink
    -0.33
    ectady
    -0.33
     célula
    -0.32
     neler
    -0.32
    Халык
    -0.32
     résine
    -0.31
    POSITIVE LOGITS
     should
    1.08
    Should
    1.06
     Should
    1.05
    should
    1.02
    hould
    0.93
     SHOULD
    0.81
     fhould
    0.79
     sollte
    0.79
     ſhould
    0.77
     ought
    0.75
    Act Density 0.130%

    No Known Activations