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

    Neuronpedia

    INDEX
    Explanations

    words related to qualities or states of being that are unchangeable or unwavering

    oai_token-act-pair · gpt-3.5-turbo

    phrases that signify the concept of "independence."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.79
     Lumpur
    -0.70
    BuyableInstoreAndOnline
    -0.67
    Gallery
    -0.61
    TION
    -0.58
     Later
    -0.56
     inference
    -0.54
     McGee
    -0.54
     drafts
    -0.54
    MQ
    -0.52
    POSITIVE LOGITS
    etermin
    1.26
    ignant
    1.11
    ented
    1.04
    irection
    0.99
    ivid
    0.99
    ocument
    0.93
    igent
    0.92
    orable
    0.91
    ol
    0.90
    esc
    0.89
    Act Density 0.012%

    No Known Activations