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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "That is how" followed by a strong opinion or personal perspective

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate explanations or descriptions of processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Quest
    -0.63
    room
    -0.62
    effects
    -0.60
    artifacts
    -0.60
    wear
    -0.57
     hereafter
    -0.57
     yak
    -0.57
    actor
    -0.57
    iston
    -0.56
    oris
    -0.56
    POSITIVE LOGITS
    beit
    0.71
    ativity
    0.69
    pedia
    0.69
    HCR
    0.68
    erest
    0.67
    soever
    0.66
    bill
    0.64
    ls
    0.62
    pher
    0.61
     much
    0.61
    Act Density 0.030%

    No Known Activations