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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal responsibility and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "you" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assembly
    -0.76
    ħ
    -0.65
     Dimension
    -0.65
    rss
    -0.64
    icy
    -0.64
    ftime
    -0.64
    ice
    -0.64
     AU
    -0.62
     Eag
    -0.61
     Associated
    -0.61
    POSITIVE LOGITS
    're
    1.52
    've
    1.33
    'll
    1.19
    'd
    1.08
     owe
    1.00
     encount
    0.98
    tub
    0.94
     know
    0.92
     intend
    0.91
     contrace
    0.91
    Act Density 0.241%

    No Known Activations