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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating satisfaction, approval, or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers expressing strong positive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.89
    ansas
    -0.80
    heid
    -0.78
    arthed
    -0.67
     Receiver
    -0.67
    lessly
    -0.67
    arian
    -0.66
    adelphia
    -0.66
    icipated
    -0.66
    anwhile
    -0.65
    POSITIVE LOGITS
     appreciated
    0.77
     liked
    0.76
     pissed
    0.72
     messed
    0.72
     freaking
    0.72
     darn
    0.70
     fucking
    0.70
     fuckin
    0.70
    nice
    0.69
    FTWARE
    0.69
    Act Density 0.056%

    No Known Activations