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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations, particularly concerning oceans or continents

    oai_token-act-pair · gpt-3.5-turbo

    words related to geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mson
    -0.80
    kson
    -0.74
    ãĤµ
    -0.73
    CLE
    -0.71
    jriwal
    -0.67
    ttle
    -0.62
    HCR
    -0.62
    GBT
    -0.59
    glers
    -0.59
    ======
    -0.58
    POSITIVE LOGITS
    ragon
    1.04
    ering
    1.00
    orf
    0.99
    erer
    0.91
    iverse
    0.85
    iscover
    0.83
    erers
    0.82
    oggles
    0.82
    rive
    0.81
    ition
    0.81
    Act Density 0.033%

    No Known Activations