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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating familial relationships and living situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ott
    -0.15
    iger
    -0.15
    Ñİ
    -0.14
     or
    -0.14
    ipt
    -0.14
    iffer
    -0.14
     Dong
    -0.14
     Spielberg
    -0.14
    itor
    -0.14
    -0.14
    POSITIVE LOGITS
    722
    0.17
    578
    0.17
    AYER
    0.16
    ÐĽÐŀ
    0.15
    æľ¯
    0.14
    .LoadScene
    0.14
     gim
    0.14
     اخÙĦاÙĤ
    0.14
    497
    0.14
    &W
    0.14
    Act Density 0.060%

    No Known Activations