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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions or events recounted by people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLOSE
    -0.66
     Harbor
    -0.63
    Enlarge
    -0.59
    cies
    -0.58
    prototype
    -0.57
    haven
    -0.56
    kat
    -0.56
    gone
    -0.56
     Drupal
    -0.56
    import
    -0.56
    POSITIVE LOGITS
    ictions
    1.05
     sarcast
    0.96
     omin
    0.87
    resso
    0.83
     emphatically
    0.78
     bluntly
    0.77
    icted
    0.76
     thereto
    0.75
     insult
    0.75
    endum
    0.75
    Act Density 0.061%

    No Known Activations