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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a change or transition

    oai_token-act-pair · gpt-3.5-turbo

    empty or nonsensical text segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     preceded
    -0.74
     according
    -0.73
    iffe
    -0.73
    âĢł
    -0.71
    âĦ¢:
    -0.71
     prompted
    -0.70
     thereby
    -0.68
    udder
    -0.68
    !.
    -0.67
     greeted
    -0.66
    POSITIVE LOGITS
     biggest
    1.18
    oret
    1.15
     whole
    1.09
    resa
    1.06
     hardest
    1.05
     greatest
    1.04
     downside
    1.02
     slightest
    1.02
     majority
    0.99
     totality
    0.97
    Act Density 0.580%

    No Known Activations