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

    Neuronpedia

    INDEX
    Explanations

    documents or messages such as memos, letters, emails, and briefings

    oai_token-act-pair · gpt-3.5-turbo

    references to formal communication documents and correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    existent
    -0.63
    cause
    -0.63
    ctrl
    -0.62
    $.
    -0.61
     steroids
    -0.60
     underestimated
    -0.60
    cients
    -0.59
     brakes
    -0.58
     outweigh
    -0.58
    animate
    -0.57
    POSITIVE LOGITS
     nutshell
    0.83
    idav
    0.76
    yssey
    0.67
    iqueness
    0.62
    statement
    0.62
     shootout
    0.62
    æĪ¦
    0.60
     meanwhile
    0.60
     HuffPost
    0.60
     Variety
    0.60
    Act Density 0.169%

    No Known Activations