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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "whether or not" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.81
    ãĤ¼ãĤ¦ãĤ¹
    -0.79
    ãĥķãĤ©
    -0.76
    èĢħ
    -0.71
    nee
    -0.69
    Rus
    -0.69
    æ©
    -0.68
    anders
    -0.68
    ħĭ
    -0.67
     Catalog
    -0.67
    POSITIVE LOGITS
    theless
    0.88
     swayed
    0.82
     technically
    0.80
     necessarily
    0.77
     exactly
    0.75
     existed
    0.75
     stray
    0.74
    fy
    0.71
     interested
    0.71
     necessary
    0.70
    Act Density 0.019%

    No Known Activations