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

    Neuronpedia

    INDEX
    Explanations

    locations or names of places, particularly Guam

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ror
    -0.91
    bol
    -0.85
    chest
    -0.83
    xia
    -0.82
    ocracy
    -0.81
    opic
    -0.80
    van
    -0.80
    ton
    -0.80
    bia
    -0.79
    bed
    -0.78
    POSITIVE LOGITS
    iant
    0.82
     Guam
    0.74
    hips
    0.69
    erent
    0.69
     warr
    0.66
     Heights
    0.64
    enhagen
    0.64
     CRC
    0.64
     hots
    0.64
     neighbourhoods
    0.63
    Act Density 0.032%

    No Known Activations