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

    Neuronpedia

    INDEX
    Explanations

    details about family structure and living arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myself
    -0.18
     conc
    -0.17
     girlfriend
    -0.15
     oneself
    -0.15
    esses
    -0.14
    ä¼Ļ
    -0.14
     solo
    -0.14
    Assembly
    -0.14
     colleg
    -0.14
    football
    -0.14
    POSITIVE LOGITS
     themselves
    0.33
     their
    0.20
     thems
    0.20
     Their
    0.20
    Their
    0.20
     both
    0.19
     yourselves
    0.19
     BOTH
    0.19
    their
    0.18
     обо
    0.18
    Act Density 0.370%

    No Known Activations