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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "the" in various contexts

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

    "the...of" construction

    np_acts-logits-general · gemini-2.0-flash

    the corresponding, size, effects, associated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.71
     ſtate
    -0.66
     ſame
    -0.65
    fromnode
    -0.65
     purpoſe
    -0.62
     HttpNotFound
    -0.62
    ὖ
    -0.62
     Профиль
    -0.62
     calendriers
    -0.61
     preſent
    -0.59
    POSITIVE LOGITS
    何より
    0.78
    SequentialGroup
    0.77
    ParallelGroup
    0.70
     resulting
    0.63
     fact
    0.63
    それに
    0.62
    resulting
    0.62
     daraus
    0.61
    hra
    0.60
     חיצוניים
    0.60
    Act Density 0.349%

    No Known Activations