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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "they" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.20
    (es
    -0.18
    iana
    -0.15
    iously
    -0.14
    atti
    -0.14
    ìļ´ëĵľ
    -0.14
    andon
    -0.14
    see
    -0.13
    elly
    -0.13
    stoff
    -0.13
    POSITIVE LOGITS
     themselves
    0.23
    're
    0.19
    ’re
    0.17
    /us
    0.17
    'll
    0.17
    idelberg
    0.16
    atically
    0.16
     же
    0.15
    've
    0.15
    addtogroup
    0.15
    Act Density 0.298%

    No Known Activations