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

    Neuronpedia

    INDEX
    Explanations

    the word "It" and related pronouns indicating emphasis or importance

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

    Beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -1.04
     AssemblyCulture
    -0.97
     calendriers
    -0.87
    Tikang
    -0.84
    Hentet
    -0.84
    uxxxx
    -0.82
     Allociné
    -0.81
     TextInputType
    -0.81
    EndContext
    -0.81
    couvrez
    -0.79
    POSITIVE LOGITS
    re
    0.60
    й
    0.60
    The
    0.59
    It
    0.57
    In
    0.56
    As
    0.55
    he
    0.55
    There
    0.53
    On
    0.52
     It
    0.51
    Act Density 0.271%

    No Known Activations