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

    Neuronpedia

    INDEX
    Explanations

    uses of the comma in sentences

    oai_token-act-pair · gpt-3.5-turbo

    clauses that describe connections or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ª
    -0.74
    Ŀ
    -0.72
    raved
    -0.70
    ©¶æ
    -0.68
    andals
    -0.67
    ©
    -0.66
    leground
    -0.65
    intend
    -0.64
    sburg
    -0.64
    ocl
    -0.64
    POSITIVE LOGITS
     whereas
    1.28
     thereby
    1.12
     respectively
    1.06
     preferably
    1.01
     resulting
    0.98
     irrespective
    0.97
     regardless
    0.96
     aka
    0.91
     depending
    0.90
     whence
    0.90
    Act Density 0.462%

    No Known Activations