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

    Neuronpedia

    INDEX
    Explanations

    names of people in official or leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference formal titles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":"/
    -0.65
     basics
    -0.64
     idols
    -0.62
    zers
    -0.62
    Submit
    -0.62
    rox
    -0.62
    otin
    -0.61
     rive
    -0.61
     exposures
    -0.60
     dirt
    -0.58
    POSITIVE LOGITS
     Mehran
    0.75
     Dmitry
    0.74
    chief
    0.73
    general
    0.72
     overseeing
    0.70
     albeit
    0.70
    vice
    0.69
     Gabriel
    0.68
     Amit
    0.68
     meanwhile
    0.67
    Act Density 0.202%

    No Known Activations