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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potential or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.85
     CURIAM
    -0.83
    EDEFAULT
    -0.81
    GEBURTSDATUM
    -0.80
    tieth
    -0.80
    Lähteet
    -0.78
     Georgie
    -0.75
     azzurro
    -0.75
     Affiliations
    -0.74
    -------
    -0.74
    POSITIVE LOGITS
     can
    1.72
     CAN
    1.45
     Can
    1.38
    Can
    1.21
    can
    1.21
     may
    1.20
     be
    1.14
     could
    1.13
    ocan
    1.11
     può
    1.08
    Act Density 0.231%

    No Known Activations