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

    Neuronpedia

    INDEX
    Explanations

    references to communication and interaction processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    маз
    -0.17
    ayne
    -0.16
    ksi
    -0.15
    ainter
    -0.15
    875
    -0.15
    ynes
    -0.14
    _observer
    -0.14
    è²´
    -0.14
    /operators
    -0.14
     Rupert
    -0.14
    POSITIVE LOGITS
    /chat
    0.17
     him
    0.16
    about
    0.15
     authorities
    0.15
     tête
    0.14
     witnesses
    0.14
    _about
    0.14
     them
    0.14
     directly
    0.14
    IVITY
    0.14
    Act Density 0.062%

    No Known Activations