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

    Neuronpedia

    INDEX
    Explanations

    links to events or occurrences that cause specific reactions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ár
    -0.37
     praktik
    -0.35
     asuntos
    -0.33
     bParam
    -0.32
     biens
    -0.32
    ệc
    -0.31
     toek
    -0.31
     habitudes
    -0.30
     pratiques
    -0.29
    ceğine
    -0.29
    POSITIVE LOGITS
     trigger
    1.80
     triggering
    1.69
     Trigger
    1.65
     triggered
    1.64
     triggers
    1.63
    trigger
    1.62
    Trigger
    1.48
     Triggers
    1.45
    triggered
    1.43
    Triggers
    1.38
    Act Density 0.554%

    No Known Activations