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

    Neuronpedia

    INDEX
    Explanations

    instances of the name "Joe" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ne
    -0.20
     âĹĦ
    -0.20
    uld
    -0.18
    rikes
    -0.17
    repo
    -0.16
    竹
    -0.15
    rian
    -0.15
    room
    -0.15
    te
    -0.15
    rij
    -0.15
    POSITIVE LOGITS
     Biden
    0.21
    ctions
    0.17
     Blow
    0.17
    cken
    0.16
     fractional
    0.15
    ys
    0.15
     Rog
    0.15
     Jonas
    0.14
     Stalin
    0.14
    oload
    0.14
    Act Density 0.015%

    No Known Activations