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

    Neuronpedia

    INDEX
    Explanations

    references to anonymity and confidential information

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

    anonymous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ampingi
    -0.53
    zeiti
    -0.51
    KommentareTeilen
    -0.50
     getF
    -0.50
    ../../
    -0.50
    ../../../
    -0.49
     fallu
    -0.49
    writerow
    -0.47
     Shakspeare
    -0.47
     Artículos
    -0.46
    POSITIVE LOGITS
     anonymous
    1.15
     anonymously
    1.06
     Anonymous
    1.01
     anonymity
    0.98
    anonymous
    0.98
    Anonymous
    0.91
     anonym
    0.89
    Anonym
    0.87
    anonym
    0.85
     anony
    0.82
    Act Density 0.007%

    No Known Activations