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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erdale
    -0.15
    UMAN
    -0.15
    Äįer
    -0.14
     Ø®ÙĪاÙĨ
    -0.14
    äºŃ
    -0.14
    çĶŁçļĦ
    -0.14
    ruz
    -0.13
    alue
    -0.13
    wit
    -0.13
    HU
    -0.13
    POSITIVE LOGITS
     consecutive
    0.21
     crucial
    0.16
     ses
    0.14
     Trem
    0.14
    isis
    0.14
     proced
    0.14
    ãģĭãĤı
    0.14
    uc
    0.14
     succes
    0.14
    _ordered
    0.14
    Act Density 0.057%

    No Known Activations