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

    Neuronpedia

    INDEX
    Explanations

    quotations, especially ones related to commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks surrounding various phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.80
     chair
    -0.74
     Klu
    -0.71
     outfielder
    -0.71
     Vog
    -0.70
     Concord
    -0.70
     division
    -0.70
     candles
    -0.69
     Chair
    -0.68
     foreseeable
    -0.68
    POSITIVE LOGITS
    normal
    1.55
    cheat
    1.49
    official
    1.48
    natural
    1.40
    traditional
    1.36
    pure
    1.36
    safe
    1.36
    clean
    1.35
    classic
    1.34
    soft
    1.34
    Act Density 0.129%

    No Known Activations