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

    Neuronpedia

    INDEX
    Explanations

    mentions of interactions between entities or concepts

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

    "interaction" or "interact"

    np_acts-logits-general · gemini-2.0-flash

    interaction between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     början
    -0.61
     Substances
    -0.59
     تضيفلها
    -0.56
    stmt
    -0.56
     vägen
    -0.56
     StyleSheet
    -0.56
    isContained
    -0.55
     TDC
    -0.55
    GPP
    -0.54
     бук
    -0.54
    POSITIVE LOGITS
     interactions
    1.22
     interaction
    1.13
    Interactions
    1.09
     Interaction
    1.08
     Interactions
    1.08
    Interaction
    1.06
     Interact
    1.02
    interactions
    1.00
     interact
    1.00
    interaction
    0.98
    Act Density 0.089%

    No Known Activations