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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mlin
    -0.08
    hack
    -0.07
    sak
    -0.06
    leston
    -0.06
    ston
    -0.06
    IQ
    -0.06
    ="#">↵
    -0.06
    INU
    -0.06
     Wein
    -0.06
    ongan
    -0.06
    POSITIVE LOGITS
     Dove
    0.07
     Mezi
    0.07
    ãĥ¼ãĤ¹
    0.07
    _TAC
    0.07
    eni
    0.07
     éĻIJ
    0.07
     Ãĸr
    0.07
    _TM
    0.07
     yıldır
    0.07
    ports
    0.06
    Act Density 0.005%

    No Known Activations