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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the United States

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude or summarize information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pus
    -0.70
     overboard
    -0.59
     tom
    -0.58
    ãĤ©
    -0.55
    utterstock
    -0.55
     vectors
    -0.55
     lapt
    -0.54
     onboard
    -0.54
    bably
    -0.54
     drill
    -0.53
    POSITIVE LOGITS
    Va
    0.91
    $.
    0.84
    S
    0.83
     Geological
    0.78
    government
    0.68
    uthor
    0.66
     Soccer
    0.66
     STATES
    0.66
     Nations
    0.66
    orks
    0.65
    Act Density 0.048%

    No Known Activations