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

    Neuronpedia

    INDEX
    Explanations

    references to various types of shifts and changes, particularly in control mechanisms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XNUMX
    -0.56
     Вікі
    -0.55
    fxml
    -0.55
     Infórmanos
    -0.52
    onError
    -0.50
    الإنجليزية
    -0.49
    /**
    -0.46
     EconPapers
    -0.43
     onCancelled
    -0.42
     Corne
    -0.41
    POSITIVE LOGITS
     shift
    2.02
    shift
    1.94
     Shift
    1.89
    Shift
    1.84
     shifts
    1.71
     SHIFT
    1.71
     shifting
    1.66
     shifted
    1.63
    hift
    1.60
    shifts
    1.59
    Act Density 0.119%

    No Known Activations