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

    Neuronpedia

    INDEX
    Explanations

    proper nouns preceded by the word "the"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intage
    -0.75
    ãĥĩãĤ£
    -0.73
    allery
    -0.71
     Constantin
    -0.69
    ca
    -0.68
    foundland
    -0.68
    ACY
    -0.67
    ij士
    -0.67
    rano
    -0.66
    âĺ
    -0.63
    POSITIVE LOGITS
     structured
    0.77
     unfolded
    0.77
     stacked
    0.74
     pans
    0.72
     fared
    0.72
     stacks
    0.71
    ribed
    0.71
     differs
    0.68
     disparate
    0.67
     fragmented
    0.66
    Act Density 0.169%

    No Known Activations