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

    Neuronpedia

    INDEX
    Explanations

    instances where quantities of items are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Press
    -0.73
    Rush
    -0.69
    Barn
    -0.65
    odge
    -0.64
    Deal
    -0.63
    Chain
    -0.63
     Sadd
    -0.62
     RTX
    -0.62
     Railroad
    -0.62
     Fulton
    -0.61
    POSITIVE LOGITS
    atic
    1.08
    atically
    1.05
     selves
    0.99
    selves
    0.84
     outwe
    0.80
    atics
    0.79
     conduc
    0.78
     sinks
    0.72
     succeeded
    0.71
    azeera
    0.71
    Act Density 0.041%

    No Known Activations