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

    Neuronpedia

    INDEX
    Explanations

    references to interventions in the context of health or treatment studies

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

    intervention effects and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Égypte
    -0.47
     schuldig
    -0.44
    Sheets
    -0.37
     känna
    -0.37
    ady
    -0.36
    Sounds
    -0.35
    as
    -0.35
    Schedule
    -0.35
     Ghosts
    -0.34
     Sociological
    -0.34
    POSITIVE LOGITS
     intervention
    2.14
     Intervention
    1.93
    intervention
    1.92
    Intervention
    1.90
     intervene
    1.89
     interventions
    1.82
     intervened
    1.72
     interven
    1.69
     Interventions
    1.60
     intervención
    1.48
    Act Density 0.018%

    No Known Activations