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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "twist" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     breach
    -0.16
    inals
    -0.15
    (IService
    -0.14
     liá»ĩu
    -0.14
    auss
    -0.14
    oppers
    -0.14
    ifice
    -0.14
     widespread
    -0.14
    het
    -0.14
    Touches
    -0.14
    POSITIVE LOGITS
    -tw
    0.25
     twist
    0.24
     Twist
    0.23
     twists
    0.19
     fate
    0.19
    y
    0.18
    .tw
    0.18
    tw
    0.17
     Tw
    0.17
    Tw
    0.17
    Act Density 0.019%

    No Known Activations