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

    Neuronpedia

    INDEX
    Explanations

    words that indicate degree or extent in relation to specifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    '):
    -0.82
    "):
    -0.81
     שוליים
    -0.81
     }}"></
    -0.77
    auteuil
    -0.72
    ^(@)
    -0.71
    )");
    -0.71
    },[])
    -0.70
    ']))
    -0.69
    principalTable
    -0.69
    POSITIVE LOGITS
    gameserver
    0.59
     članak
    0.48
     maintained
    0.47
    Nig
    0.46
    databinding
    0.45
     olla
    0.45
     efic
    0.43
    b
    0.43
     tunik
    0.43
    mutex
    0.41
    Act Density 0.041%

    No Known Activations