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

    Neuronpedia

    INDEX
    Explanations

    references to monitoring or measurement activities

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     imageNamed
    -0.59
    baix
    -0.56
     monitor
    -0.54
     lari
    -0.54
     fres
    -0.52
    ẢN
    -0.50
    tvguidetime
    -0.50
    hebt
    -0.49
     Monitor
    -0.48
    tagli
    -0.47
    POSITIVE LOGITS
     monitored
    1.97
    itored
    1.11
     supervised
    0.93
    UnusedPrivate
    0.90
     tracked
    0.78
     kaynağından
    0.72
    kloped
    0.71
    parsedMessage
    0.70
     oversaw
    0.69
    Datuak
    0.66
    Act Density 0.003%

    No Known Activations