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

    Neuronpedia

    INDEX
    Explanations

    documents related to tracking in various contexts

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

    "Track" or "tracks"

    np_acts-logits-general · gemini-2.0-flash

    track and list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Morley
    -0.76
    المناصب
    -0.73
    ATURES
    -0.69
    OLIC
    -0.65
     SSM
    -0.65
     Liquids
    -0.63
    mle
    -0.62
     newValue
    -0.61
     Bolts
    -0.61
     tombé
    -0.61
    POSITIVE LOGITS
     tracks
    1.31
     Tracks
    1.30
     TRACK
    1.28
     Track
    1.26
     track
    1.23
    tracks
    1.19
    Track
    1.16
    TRACK
    1.12
    track
    1.10
     trackers
    1.05
    Act Density 0.116%

    No Known Activations