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

    Neuronpedia

    INDEX
    Explanations

    forms of the modal verbs indicating possibility or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Audiodateien
    -1.06
    \}\\
    -1.04
    )";
    -1.03
     Administrativna
    -1.02
    BibitemShut
    -1.01
    OOTDTY
    -0.94
     تانيه
    -0.93
    \"");
    -0.92
    ++)
    -0.92
    cshtml
    -0.91
    POSITIVE LOGITS
    Will
    1.05
    Can
    0.95
     Will
    0.93
     Can
    0.86
    can
    0.81
    CAN
    0.80
    May
    0.80
    Wil
    0.70
     CAN
    0.69
    will
    0.68
    Act Density 0.135%

    No Known Activations