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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACTIONS
    -0.73
     tantal
    -0.67
     pace
    -0.65
    ãĢIJ
    -0.65
    BILITIES
    -0.64
     seminal
    -0.62
     joint
    -0.62
     bruising
    -0.61
     overfl
    -0.61
     technicians
    -0.61
    POSITIVE LOGITS
    )
    0.99
    )!
    0.96
    /)
    0.95
    )."
    0.90
    ),
    0.90
    )...
    0.88
    veyard
    0.87
    Jew
    0.86
    %)
    0.85
    ,)
    0.84
    Act Density 0.080%

    No Known Activations