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

    Neuronpedia

    INDEX
    Explanations

    terminology related to scientific processes and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.71
    ↵
    -0.66
     
    -0.61
    1
    -0.59
    '
    -0.59
    )
    -0.54
     to
    -0.51
    0
    -0.50
    </em>
    -0.49
     is
    -0.48
    POSITIVE LOGITS
    <unused41>
    1.18
    <unused43>
    1.18
    <unused74>
    1.17
    <pad>
    1.17
    <unused8>
    1.17
    <unused16>
    1.16
    <unused17>
    1.16
    <unused14>
    1.16
    [@BOS@]
    1.16
    <unused3>
    1.16
    Act Density 7.587%

    No Known Activations