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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "walk" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brenner
    -0.83
     laiton
    -0.81
     jäsen
    -0.79
     miatt
    -0.79
    essentiel
    -0.78
     compleanno
    -0.78
     navideños
    -0.77
     suprême
    -0.76
     Darmstadt
    -0.75
    oldValue
    -0.75
    POSITIVE LOGITS
     walk
    1.61
     WALK
    1.54
    walk
    1.52
     Walk
    1.52
    Walk
    1.43
     walks
    1.43
     Walks
    1.42
     walked
    1.37
     walking
    1.37
    walks
    1.33
    Act Density 0.053%

    No Known Activations