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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating different approaches or methods of doing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate methods or approaches to achieve goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.94
    usters
    -0.83
    rake
    -0.72
    omore
    -0.70
     Tanz
    -0.69
    asts
    -0.67
    mare
    -0.66
    owship
    -0.63
    ulner
    -0.62
    ocument
    -0.60
    POSITIVE LOGITS
    finding
    0.86
    point
    0.79
    ward
    0.68
    finder
    0.67
    way
    0.66
    sey
    0.66
    fare
    0.63
    esa
    0.62
    forward
    0.60
    stop
    0.60
    Act Density 0.023%

    No Known Activations