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

    Neuronpedia

    INDEX
    Explanations

    references to texting or messages being sent via text

    oai_token-act-pair · gpt-3.5-turbo

    references to texting and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inion
    -0.86
    Winged
    -0.77
    Root
    -0.75
    Bush
    -0.75
    nered
    -0.74
    arist
    -0.74
    Afee
    -0.73
    Ë
    -0.72
    aldi
    -0.72
    flo
    -0.71
    POSITIVE LOGITS
     texting
    1.11
     texted
    0.97
     emailed
    0.94
    entary
    0.78
     mailed
    0.74
     blast
    0.69
    okin
    0.67
     reminders
    0.66
     Everyday
    0.65
     BART
    0.64
    Act Density 0.014%

    No Known Activations