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

    Neuronpedia

    INDEX
    Explanations

    instances of the expression "never seen before."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating unprecedented experiences or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.66
    DC
    -0.65
    hack
    -0.64
    Gab
    -0.63
    Herm
    -0.63
    PROV
    -0.63
    DIT
    -0.62
    Goal
    -0.62
    Writer
    -0.62
    Russell
    -0.61
    POSITIVE LOGITS
     sunset
    0.86
     sunrise
    0.76
     puberty
    0.75
    cies
    0.72
    ModLoader
    0.71
    heit
    0.71
     adulthood
    0.69
     embark
    0.68
     Thumbnails
    0.68
    aneously
    0.67
    Act Density 0.056%

    No Known Activations