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

    Neuronpedia

    INDEX
    Explanations

    words related to specific geographical locations, especially areas with the word "wood" in their names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various locations or entities associated with "wood"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ional
    -0.79
    Magikarp
    -0.72
     polar
    -0.71
    oresc
    -0.70
    orsche
    -0.68
     Uriel
    -0.66
    olar
    -0.65
     Mehran
    -0.62
     xen
    -0.62
     kindred
    -0.60
    POSITIVE LOGITS
    mere
    1.00
    vale
    0.98
    hurst
    0.92
     Springs
    0.91
    wood
    0.90
     Preferred
    0.87
    leigh
    0.86
    stock
    0.86
    working
    0.83
    seed
    0.83
    Act Density 0.017%

    No Known Activations