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

    Neuronpedia

    INDEX
    Explanations

    initials and abbreviated terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of quoted speech or phrases surrounded by apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵĺ
    -0.48
    Ĥİ
    -0.45
    NetMessage
    -0.40
     Pwr
    -0.40
     Pastebin
    -0.39
    EStream
    -0.38
     tradem
    -0.36
     Pv
    -0.35
     Seym
    -0.34
     pse
    -0.34
    POSITIVE LOGITS
    rous
    0.41
    rug
    0.38
    vest
    0.38
    ru
    0.37
    isco
    0.37
    gins
    0.37
    ividual
    0.37
    uart
    0.37
    ahn
    0.37
    unn
    0.37
    Act Density 2.513%

    No Known Activations