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

    Neuronpedia

    INDEX
    Explanations

    words indicating possibility or likelihood

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

    may followed by be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ——
    -0.34
    -----
    -0.33
    The
    -0.33
     éc
    -0.32
    Dés
    -0.32
    治
    -0.31
    In
    -0.31
     dérou
    -0.31
     handleSubmit
    -0.31
    いい
    -0.30
    POSITIVE LOGITS
     may
    1.27
     might
    1.05
     MAY
    1.04
     May
    1.01
    may
    0.98
    May
    0.96
    อาจ
    0.94
     Might
    0.93
    Might
    0.90
     MIGHT
    0.89
    Act Density 0.079%

    No Known Activations