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

    Neuronpedia

    INDEX
    Explanations

    governmental or political-related terms

    oai_token-act-pair · gpt-3.5-turbo

    the article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.87
    thood
    -0.76
     besides
    -0.76
    verage
    -0.74
    coins
    -0.74
    itars
    -0.72
    terness
    -0.71
    worth
    -0.70
    scape
    -0.68
    abi
    -0.68
    POSITIVE LOGITS
     aforementioned
    1.10
     respective
    0.96
     likes
    0.96
     outset
    0.96
     same
    0.96
     latter
    0.94
     Department
    0.89
     Clintons
    0.88
     National
    0.86
     United
    0.84
    Act Density 0.204%

    No Known Activations