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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions and taking action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or critique regarding societal issues and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sole
    -0.79
    soType
    -0.75
     Attribution
    -0.70
    ledged
    -0.69
    iban
    -0.66
     hailed
    -0.65
    lor
    -0.65
    ithe
    -0.65
     indistinguishable
    -0.64
     applaud
    -0.64
    POSITIVE LOGITS
     Otherwise
    1.10
     Luckily
    1.07
     Ideally
    1.02
     Fortunately
    0.93
     preferably
    0.92
     Thankfully
    0.86
    Otherwise
    0.79
     lest
    0.78
    roman
    0.74
     Normally
    0.70
    Act Density 0.668%

    No Known Activations