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

    Neuronpedia

    INDEX
    Explanations

    instances where announcements are made

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "announcing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.75
    enne
    -0.64
    ++
    -0.62
    --------------------------------------------------------
    -0.61
    ++;
    -0.60
    use
    -0.59
     lived
    -0.58
    psy
    -0.58
    ims
    -0.56
     use
    -0.56
    POSITIVE LOGITS
     announcing
    3.47
     unveiling
    1.90
     announce
    1.75
     proclaiming
    1.73
     declaring
    1.71
     announces
    1.69
     introducing
    1.68
     announcements
    1.66
     announcement
    1.66
     disclosing
    1.57
    Act Density 0.013%

    No Known Activations