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

    Neuronpedia

    INDEX
    Explanations

    technical phrases related to work or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate predictions or expectations about future outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pires
    -0.59
     Sina
    -0.57
     allegedly
    -0.56
    inus
    -0.55
    CHA
    -0.54
    sych
    -0.54
    afia
    -0.54
    oons
    -0.53
    pired
    -0.50
    Privacy
    -0.49
    POSITIVE LOGITS
     someday
    1.06
     anytime
    0.93
     sooner
    0.85
     sometime
    0.82
    omever
    0.77
     whatever
    0.76
     tomorrow
    0.75
     whichever
    0.74
     accordingly
    0.74
     ASAP
    0.73
    Act Density 1.071%

    No Known Activations