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 reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oil
    -0.67
    oint
    -0.66
     ILCS
    -0.65
    bol
    -0.62
    adies
    -0.61
     ordinances
    -0.59
     marriages
    -0.59
    wcsstore
    -0.58
    taboola
    -0.58
     pend
    -0.57
    POSITIVE LOGITS
     sarcast
    1.04
     bluntly
    0.99
     aloud
    0.84
     rhet
    0.80
     omin
    0.76
     emphatically
    0.74
     paraph
    0.73
     è£ıè
    0.73
     angrily
    0.72
     crypt
    0.70
    Act Density 0.182%

    No Known Activations