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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or official processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.84
     âĢº
    -0.73
    itars
    -0.72
     besides
    -0.72
    abi
    -0.71
    ations
    -0.69
    ata
    -0.68
     solves
    -0.67
    verage
    -0.66
    heit
    -0.66
    POSITIVE LOGITS
     aforementioned
    0.99
     latter
    0.95
     slightest
    0.95
     respective
    0.93
     likes
    0.91
     same
    0.91
     outset
    0.86
    ses
    0.85
     Clintons
    0.83
     afore
    0.82
    Act Density 0.179%

    No Known Activations