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

    Neuronpedia

    INDEX
    Explanations

    references to returning to a previous state or normalcy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unterschied
    -0.45
     tambahan
    -0.43
     hindurch
    -0.42
     Hintergrund
    -0.41
     arrivare
    -0.39
     resulting
    -0.39
    reactstrap
    -0.39
     llegar
    -0.39
     supplémentaire
    -0.38
     zatím
    -0.38
    POSITIVE LOGITS
     normalcy
    1.00
     normality
    0.99
     normalidad
    0.82
     basics
    0.78
     semula
    0.75
     normal
    0.74
     lost
    0.72
     original
    0.70
     familiar
    0.70
    原来的
    0.70
    Act Density 0.328%

    No Known Activations