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

    Neuronpedia

    INDEX
    Explanations

    the word "In" in various contexts, indicating the presence of time or place references

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

    starting phrases or clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BibitemShut
    -0.70
    -0.68
     AssemblyCulture
    -0.61
    SBATCH
    -0.58
    mpagne
    -0.57
     müſſen
    -0.56
     Weiſe
    -0.55
     Pelop
    -0.55
    <unused41>
    -0.54
    <unused74>
    -0.54
    POSITIVE LOGITS
     In
    0.85
    In
    0.57
     If
    0.55
     For
    0.55
     On
    0.53
     As
    0.47
     To
    0.45
    For
    0.45
     At
    0.43
    On
    0.43
    Act Density 0.115%

    No Known Activations