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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and international relations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !!!
    -0.74
    leeve
    -0.74
     besides
    -0.72
    tackle
    -0.70
    !!!!!
    -0.70
    !!!!
    -0.69
     partName
    -0.68
     because
    -0.67
     âĢº
    -0.66
    !!
    -0.65
    POSITIVE LOGITS
     latter
    1.50
     aforementioned
    1.19
     same
    1.11
     slightest
    1.10
     entirety
    0.98
     remainder
    0.97
     ensuing
    0.95
     likes
    0.94
     country
    0.93
     nation
    0.91
    Act Density 1.028%

    No Known Activations