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

    Neuronpedia

    INDEX
    Explanations

    a variety of forms of the verb "have" in different contexts

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

    Followed by indefinite articles

    np_acts-logits-general · gemini-2.0-flash

    have: article/quantifier/state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.19
    AddTagHelper
    -0.94
    脚注の使い方
    -0.93
     itſelf
    -0.91
     ſtate
    -0.82
     myſelf
    -0.81
    ագրություններ
    -0.80
     '\\;'
    -0.80
     <<<<<<<<<<<<<<
    -0.80
     purpoſe
    -0.76
    POSITIVE LOGITS
     a
    1.15
     an
    1.09
     the
    0.91
     some
    0.77
     
    0.77
     much
    0.76
     more
    0.73
     great
    0.70
    Tiene
    0.66
     one
    0.63
    Act Density 0.249%

    No Known Activations