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

    Neuronpedia

    INDEX
    Explanations

    words related to categorization and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ially
    -0.07
    oog
    -0.06
    ALLY
    -0.06
    ayan
    -0.05
    omorphic
    -0.05
     gas
    -0.05
     che
    -0.05
    branch
    -0.05
     kh
    -0.05
     gymn
    -0.05
    POSITIVE LOGITS
    kening
    0.08
    ØŃات
    0.08
    imento
    0.07
    Ñĩив
    0.07
     Loose
    0.07
    inkel
    0.07
    ecast
    0.07
    ingen
    0.07
    kan
    0.07
    ulong
    0.07
    Act Density 0.043%

    No Known Activations