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

    Neuronpedia

    INDEX
    Explanations

    terms indicating structural or physical attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owell
    -0.16
     Yates
    -0.15
     Olson
    -0.15
    lessness
    -0.14
    oa
    -0.14
    iness
    -0.14
    kova
    -0.14
    597
    -0.14
    isy
    -0.14
    ductive
    -0.14
    POSITIVE LOGITS
    -wise
    0.43
     wise
    0.40
    wise
    0.39
    ewise
    0.36
    wards
    0.35
    istically
    0.35
    atically
    0.34
    aneously
    0.34
    lessly
    0.32
    ensively
    0.31
    Act Density 0.232%

    No Known Activations