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

    Neuronpedia

    INDEX
    Explanations

    the word "record" appearing in various contexts

    oai_token-act-pair · gemini-2.0-flash

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     record
    -1.23
    record
    -0.98
     recording
    -0.97
    recorded
    -0.93
     recorded
    -0.93
     records
    -0.85
    recording
    -0.81
     RECORD
    -0.79
    Recording
    -0.77
     Record
    -0.76
    POSITIVE LOGITS
     itſelf
    1.27
     faſt
    1.26
     Anſ
    1.23
     Monfieur
    1.20
     Reſ
    1.18
     purpoſe
    1.16
     Majefty
    1.16
     myſelf
    1.14
    ſelf
    1.14
     iſt
    1.14
    Act Density 1.531%

    No Known Activations