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

    Neuronpedia

    INDEX
    Explanations

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

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

    change or movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onError
    -0.60
    er
    -0.52
    fxml
    -0.50
     onError
    -0.47
    ola
    -0.47
    yn
    -0.47
    yon
    -0.47
     Infórmanos
    -0.46
    onic
    -0.46
    usan
    -0.45
    POSITIVE LOGITS
     shift
    1.22
    shift
    1.18
     Shift
    1.16
    Shift
    1.16
     SHIFT
    1.09
    hift
    1.05
    shifting
    1.01
     shifts
    1.00
     shifting
    0.97
    SHIFT
    0.97
    Act Density 0.018%

    No Known Activations