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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns that refer to the subject of a clause or sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    immel
    -0.18
    nc
    -0.16
    ford
    -0.15
    ubl
    -0.15
    avana
    -0.15
    ло
    -0.15
    ju
    -0.14
    val
    -0.14
    uen
    -0.14
    ito
    -0.14
    POSITIVE LOGITS
    -même
    0.30
    zelf
    0.29
    /us
    0.21
    adık
    0.18
    SELF
    0.17
    zÅij
    0.17
    aly
    0.16
    self
    0.16
    elf
    0.16
    Å¡Å¥
    0.15
    Act Density 0.048%

    No Known Activations