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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating caution or things to monitor

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

    watch out for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     she
    -0.35
    ThroughAttribute
    -0.35
    눠
    -0.34
    기를
    -0.32
    '}';
    -0.32
     tkinter
    -0.32
    currentPage
    -0.31
     apartment
    -0.31
     France
    -0.31
    endsection
    -0.31
    POSITIVE LOGITS
     spotting
    0.66
     Spot
    0.60
     pozor
    0.56
     Spotted
    0.56
     invariants
    0.56
     Observation
    0.53
     spots
    0.53
    Spot
    0.53
    Spotted
    0.53
    spots
    0.52
    Act Density 0.006%

    No Known Activations