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

    Neuronpedia

    INDEX
    Explanations

    names of specific locations or people, especially ending in 'mond'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations or proper nouns related to urban areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NRS
    -0.84
    Magikarp
    -0.78
    76561
    -0.72
    Alien
    -0.63
    glers
    -0.61
    ngth
    -0.59
     Bravo
    -0.59
    externalActionCode
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.59
     Adin
    -0.57
    POSITIVE LOGITS
    ieth
    1.13
    iate
    1.02
    mond
    1.01
    ijk
    0.90
    gow
    0.87
    ocument
    0.86
    iated
    0.85
    iac
    0.84
    iership
    0.83
    e
    0.79
    Act Density 0.013%

    No Known Activations