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

    Neuronpedia

    INDEX
    Explanations

    references to checks in various contexts

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

    check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    void
    -0.56
    sterdam
    -0.51
    orst
    -0.50
     SOA
    -0.50
    arns
    -0.49
    uram
    -0.48
    getMinutes
    -0.48
    bitan
    -0.48
    oas
    -0.47
    initialState
    -0.47
    POSITIVE LOGITS
     check
    1.83
     Check
    1.73
    check
    1.70
    Check
    1.70
     CHECK
    1.49
    CHECK
    1.37
     checks
    1.36
     Checks
    1.30
     checked
    1.27
    チェック
    1.22
    Act Density 0.018%

    No Known Activations