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

    Neuronpedia

    INDEX
    Explanations

    dashes, particularly in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ã
    -1.06
     Â
    -0.74
     <?=
    -0.73
    tonsoft
    -0.71
     Duran
    -0.70
     {}",
    -0.70
     ´
    -0.68
    ли
    -0.65
     +/-
    -0.65
    Ã
    -0.65
    POSITIVE LOGITS
    —
    1.50
    ”—
    1.50
    !—
    1.49
    ?—
    1.48
    )—
    1.40
    —(
    1.38
    —“
    1.32
    ,—
    1.27
    ​—
    1.26
    "—
    1.26
    Act Density 0.191%

    No Known Activations