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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potentiality or ability

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

    Modal verbs (is, are, might, could, were, would)

    np_acts-logits-general · gemini-2.0-flash

    describes states or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </>
    -0.53
     oprot
    -0.48
    </>
    -0.46
    ztus
    -0.45
    ArrowToggle
    -0.45
     picky
    -0.45
     cheerful
    -0.45
     Administrativna
    -0.45
     ***!
    -0.44
     Moab
    -0.44
    POSITIVE LOGITS
     will
    0.48
    afficheront
    0.46
     is
    0.46
    ніципалі
    0.44
     belangrij
    0.43
     NSCoder
    0.42
     can
    0.41
     cannot
    0.41
     vendar
    0.40
     has
    0.39
    Act Density 0.963%

    No Known Activations