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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unner
    -0.16
    iper
    -0.15
    ipers
    -0.14
    332
    -0.13
    irsch
    -0.13
    ropa
    -0.13
    316
    -0.13
    ropp
    -0.13
    141
    -0.13
    arm
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĤ¸
    0.16
    klär
    0.15
    acco
    0.15
     Counts
    0.14
    ̣
    0.14
    į¼
    0.14
    _nth
    0.13
    ¾
    0.13
    495
    0.13
    ãĥ£
    0.13
    Act Density 0.101%

    No Known Activations