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

    Neuronpedia

    INDEX
    Explanations

    discussions about online community activities and various technical terms

    oai_token-act-pair · gpt-3.5-turbo

    numerical references or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adversaries
    -0.86
     inward
    -0.80
     separated
    -0.77
     retail
    -0.76
     aides
    -0.75
     institutions
    -0.73
     adversary
    -0.73
     outward
    -0.72
     enterprises
    -0.71
     headquartered
    -0.70
    POSITIVE LOGITS
     Quote
    1.26
    Hi
    1.22
    Hello
    1.19
    nice
    1.13
    wow
    1.05
    HAHA
    1.04
    Nice
    1.04
    Quote
    1.03
    Awesome
    1.02
    Dear
    1.02
    Act Density 0.173%

    No Known Activations