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

    Neuronpedia

    INDEX
    Explanations

    references to components or segments of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.53
    \}\\
    -0.46
     sens
    -0.45
    }*/
    -0.44
     '
    -0.43
    ••••
    -0.43
    aland
    -0.43
     panas
    -0.43
     laten
    -0.43
     cross
    -0.43
    POSITIVE LOGITS
     borders
    0.88
     doors
    0.88
     skies
    0.82
     Skies
    0.78
    InjectAttribute
    0.77
    بوابة
    0.77
    piece
    0.74
     avoient
    0.74
     Vin
    0.73
    Vin
    0.73
    Act Density 0.092%

    No Known Activations