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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "walk" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brenner
    -0.92
     miatt
    -0.85
     laiton
    -0.85
     Darmstadt
    -0.85
    essentiel
    -0.84
     navideños
    -0.81
     religiosos
    -0.80
     suprême
    -0.79
     jäsen
    -0.78
     fantaisie
    -0.78
    POSITIVE LOGITS
     walk
    1.69
    walk
    1.62
     WALK
    1.62
     Walk
    1.61
    Walk
    1.52
     walks
    1.49
     walked
    1.46
     walking
    1.46
     Walks
    1.45
    WALK
    1.39
    Act Density 0.044%

    No Known Activations