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

    Neuronpedia

    INDEX
    Explanations

    symbols or punctuation marks used to convey emphasis or separation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kendal
    -0.96
    AndEndTag
    -0.95
    Obrázky
    -0.94
     Lesley
    -0.93
     Elgin
    -0.90
    ytale
    -0.89
    -0.89
    -0.88
    ázquez
    -0.88
     Lordships
    -0.88
    POSITIVE LOGITS
     —
    1.80
    ———
    1.11
    ————————————————
    1.07
     —,
    1.01
     ==
    0.99
    —————
    0.97
    ————
    0.95
    ——
    0.94
    ————————
    0.89
    ly
    0.86
    Act Density 0.157%

    No Known Activations