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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and inventions

    oai_token-act-pair · gpt-3.5-turbo

    periods or sentences ending with a punctuation mark

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compr
    -0.82
     neighb
    -0.78
     redes
    -0.77
     ogre
    -0.77
     nodd
    -0.76
     prey
    -0.76
     tyr
    -0.75
     cabbage
    -0.75
     challeng
    -0.74
    uers
    -0.74
    POSITIVE LOGITS
     Firstly
    1.23
     Located
    1.22
     Specifically
    1.19
     Its
    1.19
     Typically
    1.11
     Whilst
    1.09
     Normally
    1.09
     Previously
    1.09
     Especially
    1.08
     Whereas
    1.08
    Act Density 0.800%

    No Known Activations