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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to engagement and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilder
    -0.14
    ANTE
    -0.14
    ibr
    -0.14
    ebra
    -0.13
    auf
    -0.13
     Huffman
    -0.13
     bfs
    -0.13
     اÙĦدر
    -0.13
    abe
    -0.13
    ANJI
    -0.13
    POSITIVE LOGITS
     towards
    0.16
    éĢ²è¡Į
    0.15
     Conduct
    0.15
     пÑĢоведениÑı
    0.15
     fora
    0.15
    ledge
    0.15
    azen
    0.15
    iaux
    0.15
    uada
    0.15
    illisecond
    0.14
    Act Density 0.248%

    No Known Activations