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

    Neuronpedia

    INDEX
    Explanations

    hiking-related activities and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downhill
    -0.15
     rode
    -0.15
    eve
    -0.15
    eyed
    -0.15
    azeera
    -0.14
     dive
    -0.14
     dives
    -0.14
    borg
    -0.14
    ausal
    -0.14
    aqu
    -0.13
    POSITIVE LOGITS
     path
    0.18
     paths
    0.17
    shortcut
    0.15
     hike
    0.15
     yürüy
    0.14
    oute
    0.14
    /path
    0.14
     Exploration
    0.14
    ATYPE
    0.14
     exploration
    0.14
    Act Density 0.135%

    No Known Activations