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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "walk" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    walks: around, out, away, down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.45
    })->
    -0.41
    ensive
    -0.41
    ValueStyle
    -0.41
     pastime
    -0.40
    Hozzáférés
    -0.40
    เช่น
    -0.40
     Mühe
    -0.39
    BibitemOpen
    -0.39
    Pozdrawiam
    -0.39
    POSITIVE LOGITS
     walked
    1.16
     walk
    0.99
     WALK
    0.85
    Walk
    0.83
    walk
    0.83
     Walk
    0.81
     walks
    0.79
     walking
    0.75
    WALK
    0.71
     Walking
    0.69
    Act Density 0.008%

    No Known Activations