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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "see."

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

    see followed by reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dant
    -0.51
    lanta
    -0.50
     dav
    -0.50
     Wulf
    -0.50
    mpton
    -0.49
     թվական
    -0.48
     HDF
    -0.48
     Halifax
    -0.48
    Dakota
    -0.48
    ginal
    -0.47
    POSITIVE LOGITS
    see
    1.95
    See
    1.69
     See
    1.67
    SEE
    1.56
     see
    1.53
     SEE
    1.41
     sees
    1.20
    sees
    1.18
     siehe
    1.05
    siehe
    1.05
    Act Density 0.035%

    No Known Activations