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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to the concept of 'oddness' or 'strangeness'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arian
    -0.17
    toi
    -0.15
    raphics
    -0.15
     Mori
    -0.15
    owitz
    -0.15
    apor
    -0.15
    tee
    -0.15
    è±Ĭ
    -0.14
    ÑĤеÑĢи
    -0.14
    tered
    -0.13
    POSITIVE LOGITS
    ball
    0.41
    balls
    0.32
    yssey
    0.31
    ities
    0.30
    -ball
    0.29
    Ball
    0.23
    /e
    0.23
    ity
    0.23
    -number
    0.23
    -even
    0.23
    Act Density 0.010%

    No Known Activations