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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various activities or events, such as professional meetings, religious activities, public performances, ethical or moral problems, police actions, and political discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to structured activities and social gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arij
    -0.47
    photos
    -0.47
    ournal
    -0.46
    itialized
    -0.43
     Gamble
    -0.42
     Ré
    -0.41
    DVD
    -0.41
     caveats
    -0.41
    enery
    -0.41
     Vie
    -0.40
    POSITIVE LOGITS
    '.
    0.68
    %.
    0.62
    .</
    0.61
    .<
    0.59
     theirs
    0.57
    ().
    0.57
    +.
    0.56
    .).
    0.56
    ''.
    0.56
    ".
    0.56
    Act Density 3.240%

    No Known Activations