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

    Neuronpedia

    INDEX
    Explanations

    references to events and states unfolding over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typelib
    -0.63
    ########.
    -0.62
     defaultstate
    -0.50
     nonUne
    -0.49
    今回も
    -0.48
     defStyleAttr
    -0.47
    󠁮
    -0.47
     autorytatywna
    -0.47
    tagHelperRunner
    -0.47
    を重ね
    -0.46
    POSITIVE LOGITS
     suddenly
    3.47
     sudden
    3.20
    suddenly
    2.95
     Suddenly
    2.86
    Suddenly
    2.83
    Sudden
    2.52
    突然
    2.52
     Sudden
    2.48
     plötzlich
    2.47
     soudain
    2.45
    Act Density 0.761%

    No Known Activations