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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of ensuring or guaranteeing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.72
    TAG
    -0.69
    enge
    -0.68
    Plus
    -0.68
    aukee
    -0.66
    ãĤ»
    -0.65
    oft
    -0.62
    ARC
    -0.62
    MQ
    -0.60
    Think
    -0.59
    POSITIVE LOGITS
     whoever
    0.71
     Ensure
    0.69
     nobody
    0.67
     adequate
    0.66
    soever
    0.64
     everyone
    0.64
     unborn
    0.64
     everybody
    0.64
     we
    0.63
     survives
    0.63
    Act Density 0.079%

    No Known Activations