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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "walk"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     navideños
    -0.57
    Suspense
    -0.54
    rukt
    -0.53
    ิลปะ
    -0.52
    csname
    -0.52
     nemico
    -0.50
    feitura
    -0.50
     couronne
    -0.49
    AndEndTag
    -0.49
    erus
    -0.49
    POSITIVE LOGITS
     walk
    5.00
    walk
    4.53
     Walk
    4.49
    Walk
    4.38
     WALK
    4.30
     walks
    4.26
     walked
    4.05
    WALK
    3.89
     Walks
    3.86
    walks
    3.82
    Act Density 0.048%

    No Known Activations