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

    Neuronpedia

    INDEX
    Explanations

    terms related to compensation or reward

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compensation or rewards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forum
    -0.81
    ahead
    -0.76
    define
    -0.75
    sonian
    -0.74
    xual
    -0.73
    fman
    -0.68
    wikipedia
    -0.68
    jong
    -0.66
    abad
    -0.65
    ational
    -0.65
    POSITIVE LOGITS
     expenses
    0.84
     expense
    0.82
     guilt
    0.80
     withholding
    0.79
     debts
    0.76
     inaction
    0.74
     sins
    0.74
     costs
    0.73
     gross
    0.72
     bribe
    0.72
    Act Density 0.309%

    No Known Activations