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

    Neuronpedia

    INDEX
    Explanations

    terms of address and titles used in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oft
    -0.18
    agger
    -0.16
    ailability
    -0.16
    ullet
    -0.16
     ÑģобоÑİ
    -0.15
    invert
    -0.14
    obl
    -0.14
    loo
    -0.14
    ilogy
    -0.14
    _bm
    -0.14
    POSITIVE LOGITS
    asse
    0.17
     Gardner
    0.17
    égor
    0.15
    ãĥ¤
    0.14
    .DOM
    0.14
    allis
    0.14
    \views
    0.14
    uchos
    0.13
    ãĤĩ
    0.13
    uda
    0.13
    Act Density 0.063%

    No Known Activations