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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions or emphasis on the word "each"

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

    each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arlene
    -0.49
     Marisa
    -0.49
     Linton
    -0.47
     lò
    -0.46
     Aro
    -0.46
     WMA
    -0.45
     Gron
    -0.45
     Kilo
    -0.44
     Jiao
    -0.44
    stdlib
    -0.43
    POSITIVE LOGITS
     each
    1.09
    Each
    1.07
     EACH
    1.02
     Each
    1.01
    each
    0.92
    EACH
    0.87
    Ogni
    0.86
     Ogni
    0.83
     Jedes
    0.82
     every
    0.82
    Act Density 0.045%

    No Known Activations