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

    Neuronpedia

    INDEX
    Explanations

    instances of hyphens or dashes used in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ´
    -1.03
    <?=
    -0.92
     Macle
    -0.89
    copes
    -0.88
     Leafs
    -0.87
    Obrázky
    -0.84
    Ţ
    -0.84
     Elgin
    -0.84
     Dominguez
    -0.84
     <?=
    -0.84
    POSITIVE LOGITS
     —
    1.11
    —
    1.10
    ———
    1.09
    ”—
    0.97
    )—
    0.96
    —”
    0.96
    —“
    0.93
    —————
    0.91
    
    0.88
    ——
    0.86
    Act Density 0.030%

    No Known Activations