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

    Neuronpedia

    INDEX
    Explanations

    dashes or hyphens in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     P
    -0.64
     de
    -0.61
     sub
    -0.58
     $\
    -0.57
     p
    -0.56
     of
    -0.55
     $
    -0.55
     in
    -0.54
     L
    -0.54
     B
    -0.54
    POSITIVE LOGITS
    —
    2.03
    --
    1.96
    ––
    1.93
    —-
    1.91
    ”—
    1.91
    ——
    1.88
    ,—
    1.82
    !—
    1.81
    )—
    1.80
    ,--
    1.77
    Act Density 0.190%

    No Known Activations