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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific place name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Oak," indicating a focus on a specific location or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enance
    -0.88
    è¦ļéĨĴ
    -0.78
    ĸļ
    -0.74
    ozyg
    -0.73
    SHIP
    -0.72
    anmar
    -0.71
    vous
    -0.68
     exagger
    -0.67
    glomer
    -0.65
    effective
    -0.64
    POSITIVE LOGITS
    sterdam
    1.18
    vale
    1.12
    wood
    1.00
    ridge
    0.99
    leaf
    0.99
     Ridge
    0.98
    bridge
    0.97
    Oak
    0.97
    tree
    0.94
    leigh
    0.94
    Act Density 0.016%

    No Known Activations