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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "walk" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     upward
    -0.19
    éĻµ
    -0.16
    座
    -0.16
    wards
    -0.15
     Extras
    -0.14
    rek
    -0.14
    itu
    -0.14
     inward
    -0.14
     climbing
    -0.13
    Extern
    -0.13
    POSITIVE LOGITS
     past
    0.29
     down
    0.27
     across
    0.26
     bare
    0.23
     through
    0.23
     around
    0.22
     along
    0.21
    past
    0.20
     circles
    0.19
     Past
    0.19
    Act Density 0.145%

    No Known Activations