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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and quantities mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to contracts and workforce statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +.
    -0.68
    $.
    -0.67
     sooner
    -0.65
    ]).
    -0.63
    .</
    -0.62
    )).
    -0.62
    '.
    -0.61
     theirs
    -0.60
     beforehand
    -0.58
    />
    -0.58
    POSITIVE LOGITS
    bernatorial
    0.57
    ovan
    0.56
    illion
    0.53
    selling
    0.51
    assador
    0.51
     of
    0.50
    luster
    0.50
    iamond
    0.50
    iple
    0.50
    UFC
    0.50
    Act Density 1.365%

    No Known Activations