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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing importance or specificity

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

    "Especially" or "particularly" introducing a reason/explanation

    np_acts-logits-general · gemini-2.0-flash

    especially, particularly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addirittura
    -0.65
     незавершена
    -0.61
    batis
    -0.59
    脚注の使い方
    -0.58
     jopa
    -0.58
     lediglich
    -0.58
     صرف
    -0.57
    TestBase
    -0.56
     persino
    -0.56
     simplemente
    -0.54
    POSITIVE LOGITS
     those
    1.04
    those
    0.82
    Those
    0.79
     Those
    0.79
     since
    0.77
     noteworthy
    0.73
     THOSE
    0.73
     considering
    0.72
     ones
    0.71
    cially
    0.70
    Act Density 0.116%

    No Known Activations