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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of determination or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "will" in various contexts, often related to authority or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reporting
    -0.72
    ¥µ
    -0.68
    aughed
    -0.67
     Composite
    -0.64
    eatures
    -0.63
    ħĭ
    -0.62
    pport
    -0.61
    ãĥĺãĥ©
    -0.61
    orget
    -0.61
     Diet
    -0.60
    POSITIVE LOGITS
    fulness
    0.97
    ows
    0.87
    power
    0.86
    iam
    0.85
    FUL
    0.83
    fully
    0.79
    ow
    0.78
    ingly
    0.78
    sburg
    0.77
    ily
    0.77
    Act Density 0.085%

    No Known Activations