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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions, characteristics, and actions of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the actions or traits of people and species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.81
    =~
    -0.74
    DEF
    -0.70
    æĪ¦
    -0.69
    ãĤ´
    -0.68
    -+
    -0.68
     ................
    -0.68
    BuyableInstoreAndOnline
    -0.67
    ĸļ
    -0.64
    =-=-=-=-=-=-=-=-
    -0.64
    POSITIVE LOGITS
    rosso
    0.78
    emo
    0.67
    inelli
    0.66
    hops
    0.64
    hop
    0.64
    iti
    0.64
    uce
    0.63
     downright
    0.63
     stray
    0.62
    eeper
    0.61
    Act Density 0.467%

    No Known Activations