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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or certainty

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     lenker
    -0.93
     Compagn
    -0.89
     pageContext
    -0.89
     мѣ
    -0.87
     تانيه
    -0.85
    tieth
    -0.82
    HHHHHHHH
    -0.81
     myſelf
    -0.81
    texte
    -0.81
    setVerticalGroup
    -0.80
    POSITIVE LOGITS
    May
    1.04
     May
    0.99
     MAY
    0.88
     Can
    0.87
     CAN
    0.85
     have
    0.85
     Will
    0.85
    MAY
    0.84
    Can
    0.83
    Will
    0.82
    Act Density 0.057%

    No Known Activations