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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal needs and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bender
    -0.17
    atel
    -0.14
    875
    -0.14
    uft
    -0.13
     mik
    -0.13
    RET
    -0.13
    inde
    -0.13
    ãĥ³ãĤ¬
    -0.13
    unden
    -0.13
    isplay
    -0.13
    POSITIVE LOGITS
    ulas
    0.17
    ood
    0.16
    unma
    0.15
    oose
    0.15
     dilig
    0.14
    ÑĤÑĸ
    0.13
     Hear
    0.13
    ukkit
    0.13
    SelectionMode
    0.13
     interesting
    0.13
    Act Density 0.019%

    No Known Activations