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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names, especially full names with titles like Jr

    oai_token-act-pair · gpt-3.5-turbo

    specific names and locations related to events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.81
    IUM
    -0.77
    ãĤ£
    -0.70
    ARP
    -0.69
    ITION
    -0.69
    ERO
    -0.68
    ãĥİ
    -0.66
     fortun
    -0.66
    RET
    -0.66
    ãĤ·ãĥ£
    -0.65
    POSITIVE LOGITS
    quartered
    0.88
    waters
    0.83
     AFB
    0.80
    prototype
    0.77
     Correctional
    0.75
     Farms
    0.73
     Wol
    0.73
     Halls
    0.72
     Cavern
    0.71
    shire
    0.70
    Act Density 0.729%

    No Known Activations