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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns and related expressions of ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مُعرِّف
    -0.62
     Référence
    -0.55
     himself
    -0.53
    的他
    -0.51
    otides
    -0.51
    felf
    -0.50
     fiance
    -0.50
    ituary
    -0.47
     kendisi
    -0.47
    vible
    -0.46
    POSITIVE LOGITS
     themselves
    1.74
     their
    1.62
    Their
    1.57
    themselves
    1.51
    their
    1.51
     Their
    1.45
     they
    1.37
    they
    1.22
     THEIR
    1.22
    彼らの
    1.20
    Act Density 0.446%

    No Known Activations