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

    Neuronpedia

    INDEX
    Explanations

    expectations or inquiries about future events or outcomes

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

    future possibilities and surprises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.75
     fashiola
    -0.69
     ddelwed
    -0.65
     الرياضيه
    -0.64
    <unused28>
    -0.63
    [@BOS@]
    -0.63
    <unused74>
    -0.63
    <unused41>
    -0.63
    <unused79>
    -0.63
    <unused8>
    -0.63
    POSITIVE LOGITS
     future
    0.47
     surprises
    0.42
     unexpected
    0.41
     sorpresas
    0.41
     unforeseen
    0.39
     next
    0.38
     Zukunft
    0.37
     neler
    0.36
     surpresa
    0.34
     projections
    0.33
    Act Density 0.016%

    No Known Activations