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

    Neuronpedia

    INDEX
    Explanations

    distances specified in miles or kilometers

    oai_token-act-pair · gpt-3.5-turbo

    geographical distances and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angelo
    -0.70
    grave
    -0.70
     defe
    -0.68
    erity
    -0.68
    rights
    -0.66
     presumption
    -0.66
     plaster
    -0.62
    Stack
    -0.61
     rocking
    -0.61
     posture
    -0.61
    POSITIVE LOGITS
     kilometers
    1.18
     km
    1.17
    km
    1.15
     kilometres
    1.12
    nm
    0.95
     nm
    0.92
     miles
    0.91
     mi
    0.87
    swick
    0.82
    kil
    0.81
    Act Density 0.044%

    No Known Activations