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

    Neuronpedia

    INDEX
    Explanations

    terms related to interactions and their different forms in various contexts

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

    interaction between and of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.53
    BibitemShut
    -0.50
     femininas
    -0.49
    IFORN
    -0.49
    ßerdem
    -0.49
    expandindo
    -0.48
     Bewußt
    -0.48
    findpost
    -0.48
     désolés
    -0.47
    BufferException
    -0.47
    POSITIVE LOGITS
     interaction
    2.06
    interaction
    1.84
     Interaction
    1.83
     interactions
    1.77
    Interaction
    1.70
     Interactions
    1.61
     interacción
    1.51
    interactions
    1.50
    Interactions
    1.49
     interact
    1.45
    Act Density 0.022%

    No Known Activations