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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns and related words

    oai_token-act-pair · gemini-2.0-flash

    personal pronouns and first-person references

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

    me

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    myself
    -0.92
     myself
    -0.91
    getMy
    -0.83
     meinem
    -0.78
     meines
    -0.77
     ผม
    -0.76
     myſelf
    -0.75
    expandindo
    -0.75
    adaptiveStyles
    -0.74
     my
    -0.73
    POSITIVE LOGITS
    ,
    0.49
    .
    0.46
    ết
    0.46
    —
    0.39
     and
    0.36
    ?
    0.35
     to
    0.33
    !
    0.33
     Wiktionnaire
    0.32
     in
    0.32
    Act Density 2.945%

    No Known Activations