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

    Neuronpedia

    INDEX
    Explanations

    the word "some" along with variations of time and vague concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     same
    -0.15
    umn
    -0.15
     sometimes
    -0.15
     terms
    -0.14
    æľīäºĽ
    -0.13
     some
    -0.13
    redentials
    -0.13
    tems
    -0.13
     Gunn
    -0.13
    avid
    -0.13
    POSITIVE LOGITS
    ones
    0.28
    place
    0.28
    hw
    0.26
     sort
    0.23
    -sort
    0.22
    kind
    0.20
    onest
    0.20
    á»iji
    0.18
    oner
    0.18
    ONE
    0.17
    Act Density 0.062%

    No Known Activations