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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to individual identity or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     selves
    -0.18
    ãĥĥãĥĪ
    -0.17
    efon
    -0.16
    ufe
    -0.15
    emachine
    -0.15
    æĩ
    -0.14
    öm
    -0.13
     mouths
    -0.13
    áºŃp
    -0.13
    theses
    -0.13
    POSITIVE LOGITS
     name
    0.18
     status
    0.17
     fate
    0.17
    rud
    0.16
    ucci
    0.16
     supporters
    0.16
     Supporters
    0.15
    ding
    0.15
    tatus
    0.14
     whereabouts
    0.14
    Act Density 0.237%

    No Known Activations