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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "distort" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugin
    -0.17
    گذ
    -0.16
    igor
    -0.16
    nier
    -0.15
    iffe
    -0.15
    ahoma
    -0.15
    AMS
    -0.15
    zig
    -0.15
    acious
    -0.15
    stock
    -0.14
    POSITIVE LOGITS
    illery
    0.27
    urb
    0.25
    iller
    0.25
    inct
    0.25
    urbed
    0.24
     dist
    0.23
    ortion
    0.23
    (dist
    0.22
    ritos
    0.22
    illing
    0.22
    Act Density 0.010%

    No Known Activations