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

    Neuronpedia

    INDEX
    Explanations

    individual references and personal pronouns in the text

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

    Possessive pronouns followed by a verb/noun

    np_acts-logits-general · gemini-2.0-flash

    owner of next word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.65
    #+#
    -0.61
    UrlResolution
    -0.59
    ValueStyle
    -0.57
    évaluateur
    -0.54
    iální
    -0.53
     ब्रेकडाउन
    -0.53
     مرئيه
    -0.52
    IntoConstraints
    -0.52
    脚注の使い方
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.46
    principalColumn
    0.36
     Chwiliwch
    0.34
     الرياضيه
    0.33
     himo
    0.33
    Zusammen
    0.32
     calls
    0.32
     upstream
    0.31
     heard
    0.29
    ellido
    0.28
    Act Density 0.220%

    No Known Activations