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

    Neuronpedia

    INDEX
    Explanations

    terms related to companies and organizations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    room
    -0.50
    4
    -0.50
    ↵
    -0.49
    ↵↵
    -0.47
    3
    -0.47
    1
    -0.46
    6
    -0.45
    <eos>
    -0.43
    c
    -0.43
    d
    -0.43
    POSITIVE LOGITS
    nologue
    0.95
    tagHelperRunner
    0.92
     Jefus
    0.90
     الحره
    0.90
     doubtnut
    0.87
     poffe
    0.86
     سكانية
    0.85
     שוליים
    0.85
     raiſ
    0.84
    parsedMessage
    0.84
    Act Density 0.030%

    No Known Activations