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

    Neuronpedia

    INDEX
    Explanations

    the word "where."

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

    introducing locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.56
    SourceChecksum
    -0.51
    又不
    -0.41
    jski
    -0.40
     cuillère
    -0.39
    -0.39
    RectangleBorder
    -0.36
     kuiten
    -0.36
     tightening
    -0.35
     ANYTHING
    -0.35
    POSITIVE LOGITS
     where
    0.76
    where
    0.74
     onde
    0.62
     где
    0.61
    الدراسه
    0.60
     όπου
    0.59
     où
    0.59
     donde
    0.58
    donde
    0.57
     Where
    0.56
    Act Density 0.030%

    No Known Activations