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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to authority and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veis
    -0.17
    apy
    -0.16
    jem
    -0.14
    _UD
    -0.14
    querque
    -0.14
    erties
    -0.14
    heid
    -0.14
    itzer
    -0.13
     altura
    -0.13
    dle
    -0.13
    POSITIVE LOGITS
    adero
    0.18
    /fw
    0.17
    etch
    0.15
     Stam
    0.14
     Duffy
    0.14
    andest
    0.14
    kea
    0.14
    idebar
    0.14
    iale
    0.13
    enes
    0.13
    Act Density 0.016%

    No Known Activations