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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and references relating to proofs or theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ped
    -0.15
    bane
    -0.14
    oo
    -0.14
    ümÃ¼ÅŁ
    -0.14
    oya
    -0.14
    744
    -0.14
    ä¼ģ
    -0.14
     Gree
    -0.13
    _ED
    -0.13
     Geile
    -0.13
    POSITIVE LOGITS
    å¼ı
    0.20
     above
    0.18
    eq
    0.17
    isoft
    0.17
    ODE
    0.16
    asan
    0.16
    Eq
    0.16
    ç
    0.15
    iej
    0.15
     defining
    0.15
    Act Density 0.122%

    No Known Activations