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

    Neuronpedia

    INDEX
    Explanations

    statements made by entities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    statements or declarations made by various organizations or officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.81
    âĶĢâĶĢâĶĢâĶĢ
    -0.70
    nian
    -0.65
    âī
    -0.65
     haun
    -0.62
     Himself
    -0.61
    pocket
    -0.59
    cffffcc
    -0.58
    gling
    -0.58
     he
    -0.58
    POSITIVE LOGITS
     its
    1.15
    Its
    1.11
     Its
    1.06
     statement
    1.05
     ITS
    0.88
     filings
    0.85
     itself
    0.84
     newsletter
    0.83
     broch
    0.82
    Statement
    0.81
    Act Density 0.189%

    No Known Activations