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

    Neuronpedia

    INDEX
    Explanations

    references to complex legal or political concepts related to accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.54
     المعيارى
    -0.53
    >
    -0.48
    ########.
    -0.48
    UserScript
    -0.48
     trypsin
    -0.47
    исленность
    -0.47
     SwitchCompat
    -0.47
    ьажоргаш
    -0.47
    EnableWeb
    -0.45
    POSITIVE LOGITS
     including
    0.83
    including
    0.71
     Including
    0.71
    Including
    0.65
     INCLUDING
    0.63
     incluyendo
    0.61
     включая
    0.61
     incluindo
    0.59
    INCLUDING
    0.58
     כולל
    0.57
    Act Density 0.816%

    No Known Activations