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

    Neuronpedia

    INDEX
    Explanations

    references to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.55
    as
    -0.53
    not
    -0.52
    or
    -0.51
    ck
    -0.48
    is
    -0.48
    0
    -0.48
     and
    -0.47
     Baus
    -0.47
    Red
    -0.46
    POSITIVE LOGITS
    Their
    1.83
     their
    1.76
    their
    1.69
     THEIR
    1.66
     Their
    1.66
     themselves
    1.58
    themselves
    1.53
     thier
    1.42
     theirs
    1.31
    abestanden
    1.29
    Act Density 0.085%

    No Known Activations