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

    Neuronpedia

    INDEX
    Explanations

    definite and indefinite articles in the text

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

    presence and absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.66
     faſt
    -0.65
     verſ
    -0.61
     pleaſure
    -0.61
    ########.
    -0.61
     ſte
    -0.60
     myſelf
    -0.60
     ſche
    -0.59
     tranſ
    -0.59
     Efq
    -0.59
    POSITIVE LOGITS
    fromnode
    0.43
    msgTypes
    0.41
     itself
    0.40
    @[+][
    0.38
     as
    0.38
     and
    0.35
     which
    0.35
     thereby
    0.34
    <h1>
    0.34
    nest
    0.33
    Act Density 0.118%

    No Known Activations