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

    Neuronpedia

    INDEX
    Explanations

    mentions of making bets or expressing confidence in future outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to making predictions or placing bets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.81
     Flavoring
    -0.78
    nesota
    -0.70
    pmwiki
    -0.69
    ocumented
    -0.68
    VILLE
    -0.67
    ISTER
    -0.66
     Blaze
    -0.65
    umatic
    -0.65
    ovie
    -0.64
    POSITIVE LOGITS
    hesda
    1.09
     bets
    1.04
    terson
    1.01
     bet
    0.93
    ting
    0.86
    ters
    0.85
    roth
    0.83
     peg
    0.83
    ron
    0.79
    tery
    0.78
    Act Density 0.011%

    No Known Activations