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

    Neuronpedia

    INDEX
    Explanations

    links and prompts to visit external websites

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the purpose or intent of providing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conn
    -0.85
    oln
    -0.78
    Factor
    -0.73
    orbit
    -0.69
    Bridge
    -0.69
    illin
    -0.69
    issan
    -0.69
    jam
    -0.68
    Collins
    -0.67
    itton
    -0.66
    POSITIVE LOGITS
     example
    1.06
     details
    1.05
     instance
    1.00
     awhile
    0.88
    gotten
    0.88
     clarification
    0.87
     directions
    0.86
     reasons
    0.86
     inspiration
    0.84
     updates
    0.84
    Act Density 0.074%

    No Known Activations