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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific or technical concepts

    oai_token-act-pair · gpt-3.5-turbo

    sentences with high-frequency commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jit
    -0.68
    andals
    -0.68
    USS
    -0.63
    leground
    -0.59
    raved
    -0.59
    rio
    -0.59
    ®
    -0.58
    rou
    -0.58
    rament
    -0.56
    iple
    -0.56
    POSITIVE LOGITS
     whereas
    1.36
     namely
    1.21
     regardless
    1.14
     albeit
    1.11
     thereby
    1.10
     irrespective
    1.10
     ie
    1.06
     respectively
    1.05
     aka
    1.05
     preferably
    1.02
    Act Density 0.714%

    No Known Activations