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

    Neuronpedia

    INDEX
    Explanations

    references to scientific theories and technical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orda
    -0.19
    ãĥ³ãĥĸ
    -0.17
    éis
    -0.15
    ulur
    -0.14
    rella
    -0.14
    orts
    -0.13
     tên
    -0.13
    _FACE
    -0.13
    'ya
    -0.13
    reta
    -0.13
    POSITIVE LOGITS
    ihn
    0.15
     rude
    0.15
     POLITICO
    0.15
    ãĤ¤ãĤº
    0.15
    qus
    0.14
     field
    0.14
    thinkable
    0.14
     Vanilla
    0.14
    èijĹ
    0.14
    strup
    0.13
    Act Density 0.090%

    No Known Activations