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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that provide a concluding or summarizing statement

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.91
     bul
    -0.76
     gravy
    -0.71
    allah
    -0.70
    thal
    -0.70
     maniac
    -0.69
    alian
    -0.68
    bul
    -0.67
     snake
    -0.65
     bunny
    -0.64
    POSITIVE LOGITS
     Firstly
    1.33
     Whereas
    1.33
     Suppose
    1.25
     Though
    1.13
     While
    1.10
     Whether
    1.10
     First
    1.08
     Specifically
    1.08
     Initially
    1.07
     According
    1.07
    Act Density 0.434%

    No Known Activations