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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or decisions being made

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "roll" and its variations, indicating a focus on topics related to voting or decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¤
    -0.90
    ãĤ»
    -0.80
    bub
    -0.79
    acters
    -0.72
    orial
    -0.71
    ILE
    -0.69
    ¿½
    -0.69
    bour
    -0.69
    xual
    -0.68
    ãĥŁ
    -0.67
    POSITIVE LOGITS
    sheet
    0.84
    Roll
    0.83
    roll
    0.83
     rolling
    0.79
     downhill
    0.79
    top
    0.78
    anut
    0.78
     roll
    0.78
    back
    0.77
    outs
    0.75
    Act Density 0.025%

    No Known Activations