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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidance and navigation

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

    "Your" or possessive pronouns, often misspelled

    np_acts-logits-general · gemini-2.0-flash

    your, yourself, possessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    澹
    -0.35
    참고
    -0.34
    ">—
    -0.33
     generally
    -0.33
    WebRequest
    -0.32
    ]),
    -0.31
     mostly
    -0.29
    普通に
    -0.29
    >>();
    -0.29
    Transkript
    -0.29
    POSITIVE LOGITS
     your
    0.91
     yourself
    0.71
    yourself
    0.66
     ваших
    0.66
    your
    0.65
    ſelf
    0.61
     jūsų
    0.60
    PerformLayout
    0.57
    rungsseite
    0.57
     vaše
    0.57
    Act Density 0.213%

    No Known Activations