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

    Neuronpedia

    INDEX
    Explanations

    the emphasis on the word "all" and its variations in context

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

    "All" followed by various prepositions or pronouns

    np_acts-logits-general · gemini-2.0-flash

    all sorts of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leaſt
    -1.01
     Efq
    -0.99
    EndInit
    -0.91
     ſta
    -0.90
     pleaſure
    -0.87
     raiſ
    -0.85
    OGND
    -0.84
    出版年
    -0.84
     Normdatei
    -0.84
    Portale
    -0.82
    POSITIVE LOGITS
     of
    0.87
     sorts
    0.52
     manner
    0.51
     they
    0.43
     kinds
    0.42
     we
    0.42
    ::
    0.41
     he
    0.41
    νή
    0.39
     involved
    0.38
    Act Density 0.082%

    No Known Activations