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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing feelings of similarity and differentiation among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chio
    -0.16
    imar
    -0.15
    urai
    -0.14
    ildo
    -0.14
    757
    -0.14
    ÄŁinden
    -0.14
    252
    -0.13
    URI
    -0.13
    bah
    -0.13
    uzey
    -0.13
    POSITIVE LOGITS
     ourselves
    0.36
     YOU
    0.34
     myself
    0.33
     us
    0.32
     himself
    0.31
     him
    0.30
     yourself
    0.30
     oneself
    0.30
    YOU
    0.30
     HIM
    0.28
    Act Density 0.252%

    No Known Activations