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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases ending with a period '.' that indicate a concluding statement

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and grammatical structures in the text, particularly sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.92
     earthqu
    -0.88
     servicing
    -0.83
    ufact
    -0.80
     neighb
    -0.80
    undai
    -0.79
     upgr
    -0.79
     emergency
    -0.79
    daq
    -0.78
     unloaded
    -0.78
    POSITIVE LOGITS
     Basically
    1.24
     Suppose
    1.18
     Essentially
    1.14
     Specifically
    1.14
     Perhaps
    1.10
     Anyway
    1.09
     Rather
    1.09
     Whereas
    1.08
     Firstly
    1.06
     Certainly
    1.06
    Act Density 0.633%

    No Known Activations