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

    Neuronpedia

    INDEX
    Explanations

    references to social exclusion and belonging issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajo
    -0.17
     training
    -0.16
     teaching
    -0.16
     crian
    -0.15
    aho
    -0.15
    zÄĻ
    -0.15
    ô
    -0.15
    reatest
    -0.14
    rray
    -0.14
    ibar
    -0.14
    POSITIVE LOGITS
     classmates
    0.23
     school
    0.23
     popularity
    0.20
     girls
    0.19
    school
    0.19
     class
    0.19
    åIJĮåѦ
    0.18
     School
    0.18
     Mean
    0.18
    peer
    0.18
    Act Density 0.304%

    No Known Activations