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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns, especially "you" and "me."

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

    you and us reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.57
     surla
    -0.54
    achable
    -0.54
    ReusableCell
    -0.53
    afficheront
    -0.51
    MessageTagHelper
    -0.51
     Administrativna
    -0.51
     Infórmanos
    -0.50
     محفوظة
    -0.50
     <<<<<<<<<<<<<<
    -0.50
    POSITIVE LOGITS
    YOU
    0.59
     YOU
    0.57
    ſelf
    0.56
     herself
    0.55
     yourself
    0.53
     himself
    0.52
     myſelf
    0.52
     itſelf
    0.51
    Myself
    0.51
     YOURSELF
    0.49
    Act Density 0.061%

    No Known Activations