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

    Neuronpedia

    INDEX
    Explanations

    information related to historical events, political figures, and government activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of dates or time-related phrases within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inar
    -0.70
    ertain
    -0.67
    mite
    -0.67
    iq
    -0.66
    eed
    -0.64
    olson
    -0.64
    geist
    -0.64
    imize
    -0.63
    ocations
    -0.63
    inate
    -0.62
    POSITIVE LOGITS
     flanked
    1.04
     sparking
    0.99
     shortly
    0.98
     marking
    0.97
     citing
    0.95
     prompting
    0.93
     ostensibly
    0.91
     intending
    0.90
     coinc
    0.89
     accompanied
    0.89
    Act Density 0.304%

    No Known Activations