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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exchanges or trades

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transactions or exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iard
    -0.77
    alach
    -0.71
    unt
    -0.69
    tis
    -0.67
    mins
    -0.64
    cture
    -0.63
    vironments
    -0.63
    BuyableInstoreAndOnline
    -0.63
     Ange
    -0.62
    oret
    -0.62
    POSITIVE LOGITS
    awaru
    0.86
     concessions
    0.84
     rewarded
    0.83
     assurances
    0.81
     pledges
    0.78
     offering
    0.76
    giving
    0.73
     guaranteeing
    0.73
     pledging
    0.72
     bargain
    0.71
    Act Density 0.024%

    No Known Activations