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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "I" in various contexts

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

    Sentences starting with "I"

    np_acts-logits-general · gemini-2.0-flash

    i guess, i mean, i don't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.82
    rungsseite
    -0.82
     BrowserRouter
    -0.81
    adaptiveStyles
    -0.78
     AssemblyTitle
    -0.78
    Revenir
    -0.69
    XmlAccessType
    -0.68
     محفوظة
    -0.68
    页面存档备份
    -0.67
    __*/
    -0.67
    POSITIVE LOGITS
     mean
    0.94
     don
    0.62
     remember
    0.61
     once
    0.61
    mean
    0.61
     know
    0.60
     therefore
    0.57
     hope
    0.57
     also
    0.57
     Mean
    0.57
    Act Density 0.175%

    No Known Activations