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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuation or separation within text articles

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating article continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.65
    ofi
    -0.64
    umenthal
    -0.64
    aceae
    -0.63
    wives
    -0.60
    footed
    -0.60
    asters
    -0.58
    utic
    -0.58
     mete
    -0.57
    mir
    -0.56
    POSITIVE LOGITS
     Below
    0.93
     Continued
    0.90
     Transcript
    0.74
     Loading
    0.72
     VIDEOS
    0.71
    },"
    0.68
     BELOW
    0.63
     Continue
    0.63
     Annotations
    0.63
     Story
    0.62
    Act Density 0.012%

    No Known Activations