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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the establishment or creation of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the establishment or creation of systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Herm
    -0.64
     Redmond
    -0.64
     rib
    -0.63
     bra
    -0.63
     Clapper
    -0.61
    sb
    -0.61
     regulars
    -0.60
     Yelp
    -0.60
     sclerosis
    -0.59
    square
    -0.59
    POSITIVE LOGITS
    DOWN
    0.80
    reatment
    0.78
    athering
    0.74
    illation
    0.72
    aphael
    0.71
    adle
    0.71
    iation
    0.70
    mination
    0.70
    ieth
    0.70
    fficiency
    0.69
    Act Density 0.366%

    No Known Activations