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

    Neuronpedia

    INDEX
    Explanations

    complex sentence structures and the presence of conditional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vap
    -0.18
    itate
    -0.16
    aba
    -0.16
    anic
    -0.15
     Mein
    -0.15
     Quy
    -0.14
    017
    -0.14
    raq
    -0.14
    enson
    -0.14
    444
    -0.13
    POSITIVE LOGITS
     Westbrook
    0.18
    ftware
    0.16
    ëĿ¼ëıĦ
    0.15
    istration
    0.15
     Hind
    0.14
     Henderson
    0.14
     teleport
    0.14
    Gratis
    0.14
    arios
    0.14
    ISTR
    0.14
    Act Density 0.042%

    No Known Activations