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

    Neuronpedia

    INDEX
    Explanations

    terms associated with tracking or monitoring

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

    "track" or its variations

    np_acts-logits-general · gemini-2.0-flash

    tracking and following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.49
     OMITBAD
    -0.47
    DotNetBar
    -0.47
     فريبيس
    -0.45
    izers
    -0.45
     Diss
    -0.44
    isier
    -0.43
    MemoryWarning
    -0.42
    Diss
    -0.41
    itarian
    -0.41
    POSITIVE LOGITS
     track
    2.41
     Track
    2.31
    track
    2.23
    Track
    2.22
     TRACK
    2.16
     tracks
    2.06
    TRACK
    2.03
     Tracks
    1.93
     tracked
    1.85
    Tracks
    1.79
    Act Density 0.096%

    No Known Activations