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

    Neuronpedia

    INDEX
    Explanations

    locations or places described in the text

    oai_token-act-pair · gpt-3.5-turbo

    names related to specific locations and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phia
    -0.85
    =]
    -0.85
    */(
    -0.76
    IGHT
    -0.76
    ãĥ¯ãĥ³
    -0.76
    etheless
    -0.73
    nesday
    -0.72
     Pwr
    -0.70
     DISTR
    -0.68
    ãĥī
    -0.67
    POSITIVE LOGITS
    alore
    0.99
    zhou
    0.94
    oing
    0.92
    jiang
    0.92
    aroo
    0.89
    lasses
    0.88
     Xuan
    0.87
    omez
    0.87
    eman
    0.87
    yang
    0.85
    Act Density 0.022%

    No Known Activations