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

    Neuronpedia

    INDEX
    Explanations

    titles or positions within a company

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of individuals in organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compr
    -0.66
    inka
    -0.56
     utter
    -0.55
     inval
    -0.55
     speedy
    -0.54
     strangers
    -0.52
    uder
    -0.52
     snipers
    -0.52
     mist
    -0.52
     surgeons
    -0.52
    POSITIVE LOGITS
     of
    1.16
     emer
    0.96
     Emer
    0.89
     thereof
    0.85
     OF
    0.85
    of
    0.81
    oft
    0.80
    iances
    0.76
    hips
    0.74
     &
    0.73
    Act Density 0.071%

    No Known Activations