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

    Neuronpedia

    INDEX
    Explanations

    references to the act of escaping or narrowly avoiding something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "escaped" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bench
    -0.70
    kus
    -0.70
    MA
    -0.70
     workload
    -0.67
     Vit
    -0.63
     Design
    -0.62
    review
    -0.62
     recommendation
    -0.62
     Bench
    -0.62
    design
    -0.62
    POSITIVE LOGITS
     escaped
    3.80
     escapes
    2.46
     escaping
    2.27
     escape
    2.13
     survived
    1.76
     fled
    1.73
    escape
    1.56
     Escape
    1.41
     perished
    1.41
     avoided
    1.30
    Act Density 0.018%

    No Known Activations