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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements and public announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to official gatherings or events involving notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inances
    -0.69
    gars
    -0.69
     Theft
    -0.63
     WATCH
    -0.61
     rentals
    -0.60
     itself
    -0.59
    utions
    -0.59
     patterns
    -0.58
    pmwiki
    -0.58
    direction
    -0.57
    POSITIVE LOGITS
     interviewer
    1.43
     audience
    1.29
     audiences
    1.28
     reporters
    1.07
     assembled
    1.03
     colleagues
    0.96
     listeners
    0.95
     journalists
    0.92
     crowd
    0.89
     reporter
    0.88
    Act Density 0.474%

    No Known Activations