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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ease of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uru
    -0.15
    Ø´ÙĬ
    -0.15
    LOCKS
    -0.15
    _GL
    -0.14
    lew
    -0.14
    IGN
    -0.14
    ewn
    -0.14
    лок
    -0.14
    æĶ
    -0.13
    ẩy
    -0.13
    POSITIVE LOGITS
    loh
    0.15
     Elk
    0.14
    wich
    0.14
    utin
    0.14
    hend
    0.13
    ona
    0.13
    lest
    0.13
    ieran
    0.13
    EPHIR
    0.13
    iesel
    0.13
    Act Density 0.046%

    No Known Activations