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

    Neuronpedia

    INDEX
    Explanations

    phrases describing differences and comparisons between entities or conditions

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

    "difference" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    difference between things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.61
    ließlich
    -0.52
    liesslich
    -0.51
     zvuky
    -0.46
     externi
    -0.45
    therin
    -0.45
    Corollary
    -0.45
    ̀nh
    -0.43
     Caw
    -0.43
    >//
    -0.43
    POSITIVE LOGITS
     difference
    3.59
     differences
    3.19
    difference
    3.12
     Difference
    3.01
    Difference
    2.90
     Differences
    2.86
    Differences
    2.75
     DIFFERENCE
    2.73
    differences
    2.73
     différence
    2.69
    Act Density 0.980%

    No Known Activations