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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in the context of relationships and self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oren
    -0.16
    uzzi
    -0.16
    owan
    -0.15
    mer
    -0.15
    reet
    -0.14
    reve
    -0.14
    éc
    -0.14
    ÅĻiv
    -0.14
    rist
    -0.14
    ilton
    -0.13
    POSITIVE LOGITS
    enet
    0.15
    weigh
    0.14
    ctrine
    0.14
    isque
    0.14
    ierten
    0.14
    tainment
    0.14
    .bd
    0.14
    ledged
    0.14
    Ģë¡ľ
    0.14
    ideo
    0.14
    Act Density 0.032%

    No Known Activations