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

    Neuronpedia

    INDEX
    Explanations

    descriptions of personal characteristics and behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal characteristics and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.82
    selves
    -0.77
    aughtered
    -0.75
     Spons
    -0.74
     Composite
    -0.71
     ATI
    -0.69
     Results
    -0.68
     THEIR
    -0.68
     Components
    -0.66
    heid
    -0.66
    POSITIVE LOGITS
     himself
    1.25
     deft
    1.13
     penchant
    1.02
     brist
    0.97
     esche
    0.96
     indulge
    0.96
     exasper
    0.93
     Himself
    0.92
     sly
    0.91
     rhet
    0.90
    Act Density 0.599%

    No Known Activations