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

    Neuronpedia

    INDEX
    Explanations

    statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of direct speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pes
    -0.95
    folios
    -0.90
    arette
    -0.79
    qqa
    -0.76
    haar
    -0.76
    cffffcc
    -0.75
    osponsors
    -0.75
    olen
    -0.74
    Kin
    -0.72
    mb
    -0.70
    POSITIVE LOGITS
     goodbye
    0.87
     afterward
    0.87
    NBA
    0.83
     bluntly
    0.79
     ESPN
    0.78
     Blackhawks
    0.77
     STATS
    0.76
     offseason
    0.76
     Spartan
    0.75
     sarcast
    0.75
    Act Density 0.134%

    No Known Activations