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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or potentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Armand
    -0.71
     Armand
    -0.71
     Shiro
    -0.70
     Ehr
    -0.69
    ódz
    -0.69
     horn
    -0.67
    Composable
    -0.66
     discipl
    -0.64
    totta
    -0.64
     ()
    -0.64
    POSITIVE LOGITS
     may
    1.46
     MAY
    1.35
    MAY
    1.29
    may
    1.22
     might
    1.20
    May
    1.16
     May
    1.15
     Might
    1.07
     MIGHT
    1.04
    might
    1.00
    Act Density 0.156%

    No Known Activations