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

    Neuronpedia

    INDEX
    Explanations

    terms related to interactions and relational dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zd
    -0.70
    ншни
    -0.65
     Zend
    -0.61
     fous
    -0.61
    च्या
    -0.59
     plomb
    -0.58
     vägen
    -0.57
     Ston
    -0.56
     тому
    -0.56
    штей
    -0.56
    POSITIVE LOGITS
     interaction
    1.67
     interactions
    1.66
     Interaction
    1.62
     Interactions
    1.58
     Interact
    1.55
    Interactions
    1.52
    Interaction
    1.50
     interact
    1.49
    interaction
    1.46
    interactions
    1.46
    Act Density 0.070%

    No Known Activations