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

    Neuronpedia

    INDEX
    Explanations

    phrases involving significant actions or changes related to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abant
    -0.20
    /REC
    -0.15
    _INFINITY
    -0.15
    ãģĹãģ
    -0.15
    ÑģиÑĤ
    -0.14
     неÑĤ
    -0.14
    jang
    -0.14
    å»Ĭ
    -0.14
    icro
    -0.14
    caf
    -0.14
    POSITIVE LOGITS
    758
    0.15
    incinn
    0.15
    KeyCode
    0.14
    lis
    0.14
    756
    0.14
    354
    0.14
    utting
    0.14
     Leather
    0.13
     Pocket
    0.13
     Rubin
    0.13
    Act Density 0.111%

    No Known Activations