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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases emphasizing the distinction between correlation and causation

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of conclusion or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ributes
    -0.85
     earthqu
    -0.81
     haul
    -0.78
     mosqu
    -0.77
    uers
    -0.77
     convoy
    -0.75
     awaited
    -0.74
     heir
    -0.70
     pledged
    -0.70
     corrid
    -0.70
    POSITIVE LOGITS
     Firstly
    1.30
     Specifically
    1.29
     Therefore
    1.28
     Hence
    1.24
     Whereas
    1.24
     Moreover
    1.23
     However
    1.22
     Thus
    1.22
     Typically
    1.21
     Nevertheless
    1.21
    Act Density 0.662%

    No Known Activations