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

    Neuronpedia

    INDEX
    Explanations

    instances where actions are done or considered individually or separately

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "separately."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.78
    enos
    -0.74
    IENCE
    -0.66
    wy
    -0.65
    yo
    -0.65
    eno
    -0.62
    odan
    -0.62
    ger
    -0.62
    LD
    -0.62
     Kelvin
    -0.62
    POSITIVE LOGITS
     separately
    1.00
     detach
    0.84
     guiActiveUn
    0.83
    ilitary
    0.80
     ported
    0.75
    psey
    0.74
     sexes
    0.73
     boxed
    0.71
     tang
    0.70
    comings
    0.70
    Act Density 0.002%

    No Known Activations