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

    Neuronpedia

    INDEX
    Explanations

    varying forms of the word "different" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    สือ
    -0.57
     Jib
    -0.56
    MLLoader
    -0.56
     doubtnut
    -0.55
    ség
    -0.54
     doute
    -0.53
    련
    -0.53
    revalidate
    -0.53
    ález
    -0.53
     économies
    -0.53
    POSITIVE LOGITS
    IATION
    0.84
    (!__
    0.84
     than
    0.79
     kinds
    0.78
    寻常
    0.75
    lihood
    0.74
     niż
    0.69
    than
    0.69
     sized
    0.67
     nhau
    0.66
    Act Density 0.184%

    No Known Activations