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

    Neuronpedia

    INDEX
    Explanations

    names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Woods."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otation
    -0.83
    ients
    -0.78
    ially
    -0.74
    andum
    -0.73
    inations
    -0.71
    ghai
    -0.70
    uttering
    -0.68
    ographically
    -0.68
    asta
    -0.66
    activation
    -0.66
    POSITIVE LOGITS
    hed
    0.94
    é¾
    0.83
     Hole
    0.82
    nesday
    0.81
    bury
    0.75
    schild
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.73
    itant
    0.71
     Advantage
    0.70
     APR
    0.70
    Act Density 0.058%

    No Known Activations