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

    Neuronpedia

    INDEX
    Explanations

    references to magazines and their sections

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

    magazine publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    -0.48
    helping
    -0.47
     Hull
    -0.47
     Biden
    -0.45
    ERTY
    -0.45
    sleepy
    -0.45
    this
    -0.45
    Biden
    -0.43
    sorry
    -0.42
    Protect
    -0.42
    POSITIVE LOGITS
     magazine
    1.24
     magazines
    1.20
     Magazine
    1.12
     Magazines
    1.09
    magazine
    1.08
     MAGAZINE
    1.02
    Magazine
    1.02
    MAGAZINE
    0.87
    magaz
    0.86
     Magaz
    0.86
    Act Density 0.005%

    No Known Activations