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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the word "back" in various contexts

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

    "back" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    back and forth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.84
     complaint
    -0.74
    ']))
    -0.71
    BufferException
    -0.67
    complaint
    -0.66
    ftagPool
    -0.65
    ')],
    -0.65
    ')),
    -0.64
    MeasureSpec
    -0.62
    ']),
    -0.62
    POSITIVE LOGITS
     into
    0.75
     indietro
    0.64
     forth
    0.58
     onto
    0.52
     ashore
    0.49
     Spector
    0.47
    roveň
    0.45
    tikzpicture
    0.44
    engarkan
    0.43
     Fullerton
    0.43
    Act Density 0.069%

    No Known Activations