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

    Neuronpedia

    INDEX
    Explanations

    specific locations, especially islands and provinces

    oai_token-act-pair · gpt-3.5-turbo

    names of geographical locations and administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     performer
    -0.63
     perks
    -0.62
    pread
    -0.62
     verbal
    -0.61
    oxy
    -0.61
    actic
    -0.60
     pes
    -0.60
     reprodu
    -0.60
    urally
    -0.59
    ometric
    -0.58
    POSITIVE LOGITS
     Rd
    0.98
     âĵĺ
    0.97
     Extension
    0.92
     Cemetery
    0.90
     Resort
    0.88
    ensis
    0.87
     Massacre
    0.86
     Borough
    0.84
     Junction
    0.83
     Parkway
    0.82
    Act Density 0.164%

    No Known Activations