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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal identity and group affiliation

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

    Follows conjunctions with pronouns/determiners

    np_acts-logits-general · gemini-2.0-flash

    connecting personal statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.78
    EndGlobalSection
    -0.77
     betweenstory
    -0.76
    "],
    -0.74
     متعلقه
    -0.71
     Roskov
    -0.71
    EndProject
    -0.71
    ")));
    -0.70
    ValueStyle
    -0.70
     Administrativna
    -0.70
    POSITIVE LOGITS
     looking
    0.46
     reading
    0.43
     I
    0.43
    this
    0.41
     veía
    0.39
    Loves
    0.38
     bcrypt
    0.38
     observation
    0.38
     this
    0.38
     fà
    0.38
    Act Density 0.213%

    No Known Activations