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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by descriptions or actions

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing the existence or impact of a concept or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.66
     PUBLIC
    -0.62
     guiActiveUnfocused
    -0.60
    entry
    -0.58
     Eighth
    -0.58
    duc
    -0.57
    package
    -0.57
    "],"
    -0.56
     Guant
    -0.56
     Guinea
    -0.55
    POSITIVE LOGITS
    self
    1.07
    achi
    0.98
    zbollah
    0.98
    chy
    0.96
    unes
    0.93
    iner
    0.89
    zik
    0.89
    xtap
    0.87
    asca
    0.87
    'll
    0.84
    Act Density 0.180%

    No Known Activations