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

    Neuronpedia

    INDEX
    Explanations

    the word "their" and its variations, indicating possessiveness or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bbene
    -0.57
     lebte
    -0.55
     Normdatei
    -0.52
    xk
    -0.51
     groet
    -0.49
     Navarre
    -0.48
     которому
    -0.47
    -
    -0.47
     polyg
    -0.47
     xk
    -0.47
    POSITIVE LOGITS
     their
    1.99
    Their
    1.89
     Their
    1.81
    their
    1.79
     THEIR
    1.75
     thier
    1.44
     leurs
    1.36
     ihre
    1.28
     ihrer
    1.27
     themselves
    1.25
    Act Density 0.085%

    No Known Activations