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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "be" in various forms

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

    actions to be performed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.73
     increí
    -0.72
    GOTREF
    -0.71
     avoient
    -0.69
     sánchez
    -0.69
     ainfi
    -0.68
    majánló
    -0.68
     fernández
    -0.66
    isielt
    -0.66
     indígen
    -0.64
    POSITIVE LOGITS
    ToBe
    0.66
     be
    0.62
     shall
    0.50
    ShouldBe
    0.40
    tobe
    0.40
     being
    0.38
     should
    0.38
    toBe
    0.37
     shouldBe
    0.35
     due
    0.35
    Act Density 0.040%

    No Known Activations