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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially locations and community names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ystore
    -0.16
    онÑĮ
    -0.15
    ecast
    -0.15
    linger
    -0.15
    KEN
    -0.15
    emony
    -0.14
    .tap
    -0.14
    _tolerance
    -0.14
    Titan
    -0.14
    ãĥ¼ãĥį
    -0.14
    POSITIVE LOGITS
     Hills
    0.44
     Heights
    0.44
     Springs
    0.37
     Oaks
    0.35
     Grove
    0.35
     Highlands
    0.34
     Ridge
    0.34
     Meadows
    0.33
     heights
    0.33
    dale
    0.32
    Act Density 0.104%

    No Known Activations