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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hig
    -0.67
    Classi
    -0.61
    Poss
    -0.60
     Hig
    -0.57
     
    -0.56
     opp
    -0.56
    lihood
    -0.54
    lipp
    -0.54
    ensatz
    -0.52
    Stit
    -0.52
    POSITIVE LOGITS
    ()].
    1.20
     resourceCulture
    1.14
    $.}
    1.10
    ])).
    1.09
    ']").
    1.09
    ).}
    1.04
    ))).
    1.03
    '].'
    1.02
    .'.
    1.00
    "]).
    1.00
    Act Density 0.875%

    No Known Activations