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

    Neuronpedia

    INDEX
    Explanations

    references to stages and paths in a journey or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     walks
    -0.20
     trails
    -0.19
    æº
    -0.17
     hikes
    -0.17
     footsteps
    -0.16
     Walk
    -0.16
     walk
    -0.15
     hiking
    -0.15
     walking
    -0.15
     walked
    -0.15
    POSITIVE LOGITS
     switch
    0.22
     twist
    0.19
     scenery
    0.19
     twists
    0.18
     gradual
    0.17
    switch
    0.17
    technical
    0.16
     rollers
    0.16
    adients
    0.16
     Views
    0.16
    Act Density 0.024%

    No Known Activations