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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases with commas

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.73
    odes
    -0.73
    agate
    -0.70
    orthy
    -0.68
    atcher
    -0.66
    icc
    -0.66
    ORD
    -0.64
    ORPG
    -0.64
    igator
    -0.63
    istries
    -0.62
    POSITIVE LOGITS
     alas
    1.08
     moreover
    1.01
     consequently
    0.98
     secondly
    0.97
     unsurprisingly
    0.92
     therefore
    0.90
     furthermore
    0.89
     frankly
    0.86
     preferably
    0.82
    perhaps
    0.79
    Act Density 0.097%

    No Known Activations