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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations in usage throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hig
    -0.64
     Hig
    -0.55
    Poss
    -0.55
     opp
    -0.54
    Classi
    -0.53
     SwitchCompat
    -0.52
     kond
    -0.52
    lihood
    -0.52
    <sup>
    -0.52
    (
    -0.52
    POSITIVE LOGITS
    ()].
    1.20
    $.}
    1.16
     resourceCulture
    1.15
    '].'
    1.07
    ']").
    1.05
    .'.
    1.03
    ).}
    1.03
     $-.
    1.01
    /}.
    1.00
    .".
    0.98
    Act Density 0.535%

    No Known Activations