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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups being mentioned or discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resses
    -0.17
    egin
    -0.15
    ettes
    -0.15
    arend
    -0.14
    quez
    -0.14
    hue
    -0.14
    odge
    -0.14
    lington
    -0.14
    omers
    -0.14
    thon
    -0.14
    POSITIVE LOGITS
    atically
    0.21
    /us
    0.20
    /her
    0.18
    /we
    0.17
    self
    0.17
    /th
    0.16
    OMP
    0.15
    rb
    0.15
    opause
    0.15
    inerary
    0.14
    Act Density 0.090%

    No Known Activations