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

    Neuronpedia

    INDEX
    Explanations

    sections of text related to career and historical experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    life history career

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.12
     otomatig
    -1.11
    <unused41>
    -1.02
    <unused52>
    -1.02
    <unused28>
    -1.02
    <unused14>
    -1.02
    <unused3>
    -1.02
    <unused8>
    -1.02
    [@BOS@]
    -1.02
    <pad>
    -1.02
    POSITIVE LOGITS
    </h2>
    0.34
    </strong>
    0.29
    ↵↵
    0.27
    <eos>
    0.27
    </h3>
    0.26
     Special
    0.24
    }
    0.23
    </em>
    0.23
     Resmi
    0.22
    </u>
    0.21
    Act Density 0.012%

    No Known Activations