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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "turns"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the revelation or realization of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦
    -0.73
     Odyssey
    -0.69
    heads
    -0.64
    udi
    -0.61
    ociate
    -0.61
     filibuster
    -0.56
    oscope
    -0.55
    rongh
    -0.55
    abouts
    -0.55
    ttes
    -0.55
    POSITIVE LOGITS
     raining
    0.91
     unclear
    0.73
     ironic
    0.71
     tempting
    0.71
     irony
    0.69
     beh
    0.67
     easier
    0.66
     clearer
    0.64
     coincidence
    0.64
     imperative
    0.63
    Act Density 0.254%

    No Known Activations