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

    Neuronpedia

    INDEX
    Explanations

    themes and frameworks related to mental health interventions and their evaluation

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

    preceding nouns related to systems or methods

    np_acts-logits-general · gemini-2.0-flash

    framework or checklist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.60
    enterOuterAlt
    -0.54
    SharedDtor
    -0.50
     GenerationType
    -0.49
    SharedCtor
    -0.48
    AccessFile
    -0.47
    UserScript
    -0.44
    ruptedException
    -0.44
    verifyException
    -0.44
     Wicidata
    -0.43
    POSITIVE LOGITS
     framework
    0.95
     checklist
    0.81
     frameworks
    0.79
     Framework
    0.73
     FRAMEWORK
    0.72
     checklists
    0.69
    framework
    0.69
     model
    0.68
     diagram
    0.68
    Framework
    0.66
    Act Density 0.589%

    No Known Activations