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

    Neuronpedia

    INDEX
    Explanations

    references to different fictional or real-life worlds

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" indicating different contexts or themes related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceous
    -0.79
    */(
    -0.76
    beam
    -0.66
    Wave
    -0.65
    RM
    -0.64
    amount
    -0.64
    report
    -0.64
    poon
    -0.63
    iard
    -0.62
    ctor
    -0.62
    POSITIVE LOGITS
     ours
    0.75
     sorts
    0.73
     interconnected
    0.71
     Grind
    0.70
    olation
    0.69
    uture
    0.69
    é¾į
    0.65
     Brill
    0.63
     Cul
    0.63
     disparate
    0.62
    Act Density 0.162%

    No Known Activations