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

    Neuronpedia

    INDEX
    Explanations

    descriptions of locations and road conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walk
    -0.18
     walk
    -0.18
    _walk
    -0.17
     walks
    -0.17
    ipi
    -0.16
    walk
    -0.16
     Walking
    -0.15
    herits
    -0.15
    rail
    -0.15
    lue
    -0.15
    POSITIVE LOGITS
     twist
    0.28
     dirt
    0.24
     twists
    0.24
     gravel
    0.23
     winding
    0.23
     hair
    0.23
     twisting
    0.22
    Hair
    0.22
     switch
    0.21
     Hair
    0.21
    Act Density 0.056%

    No Known Activations