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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "before" and variations related to prior occurrences or actions

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

    "before"

    np_acts-logits-general · gemini-2.0-flash

    detecting "before"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.74
     følge
    -0.73
    JspWriter
    -0.71
    ษัท
    -0.69
    genstein
    -0.65
     initComponents
    -0.65
    ptures
    -0.64
    %)$
    -0.64
    WithIOException
    -0.63
    izations
    -0.62
    POSITIVE LOGITS
    before
    1.02
     BEFORE
    0.99
     before
    0.98
     Before
    0.97
    BEFORE
    0.94
    Before
    0.91
     innan
    0.79
    andafter
    0.76
     sebelum
    0.75
    hand
    0.72
    Act Density 0.082%

    No Known Activations