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

    Neuronpedia

    INDEX
    Explanations

    instances of first-person pronouns

    oai_token-act-pair · gemini-2.0-flash

    first-person plural pronouns

    np_token-act-pair-logits · gpt-4o-mini

    we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RuleContext
    -0.55
     SqlConnection
    -0.52
     Pliny
    -0.51
    TestBed
    -0.50
     forskj
    -0.50
    LookAnd
    -0.49
    hilangan
    -0.49
    津
    -0.48
    ämie
    -0.48
     Lakeland
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.62
     utafitiHapana
    0.60
    νώ
    0.57
     highly
    0.57
     thought
    0.55
     ويكيميديا
    0.53
    észetes
    0.52
     rang
    0.51
     loved
    0.51
    neau
    0.50
    Act Density 0.619%

    No Known Activations