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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    oai_token-act-pair · gpt-3.5-turbo

    parenthetical remarks or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tack
    -0.78
     dow
    -0.75
     flock
    -0.70
     coron
    -0.68
     comparisons
    -0.68
     Maced
    -0.68
     lull
    -0.67
     Elys
    -0.67
     inund
    -0.67
     herb
    -0.66
    POSITIVE LOGITS
    sic
    1.38
    possibly
    1.36
    ...)
    1.29
    mostly
    1.29
    emphasis
    1.26
    usually
    1.26
    formerly
    1.24
    again
    1.21
    insert
    1.21
    albeit
    1.20
    Act Density 0.098%

    No Known Activations