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

    Neuronpedia

    INDEX
    Explanations

    concepts related to directed graphical models and their statistical relationships

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

    Relationships and correlations

    np_acts-logits-general · gemini-2.0-flash

    causal relationships and correlation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.46
    掬
    -0.41
    encodeWith
    -0.41
     승
    -0.39
    arture
    -0.38
     Meet
    -0.38
     TestBed
    -0.38
     Conductor
    -0.38
     Merritt
    -0.38
    enterOuterAlt
    -0.38
    POSITIVE LOGITS
     relationships
    1.33
     correlation
    1.30
     correlations
    1.29
     relationship
    1.27
     relations
    1.26
     connections
    1.21
     interdependence
    1.16
     linkages
    1.16
     relation
    1.12
    relationships
    1.11
    Act Density 1.570%

    No Known Activations