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

    Neuronpedia

    INDEX
    Explanations

    dates or mentions of specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    phrasal structures, particularly those that involve a series of items or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beir
    -0.71
     millenn
    -0.64
    iter
    -0.64
     Clarkson
    -0.60
     comprom
    -0.57
     Whitman
    -0.57
     Petty
    -0.56
    agog
    -0.56
    ifier
    -0.55
    paces
    -0.55
    POSITIVE LOGITS
    Pa
    0.86
    ,,,,
    0.85
    ::::::::
    0.85
    ,,,,,,,,
    0.81
    ::::
    0.81
    then
    0.76
    -.
    0.75
    soon
    0.75
    -)
    0.74
    tel
    0.72
    Act Density 0.049%

    No Known Activations