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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zed
    -0.16
    wheel
    -0.16
    aken
    -0.16
    ULONG
    -0.16
    ãģªãģĮãĤī
    -0.16
    аÑĢод
    -0.16
    éĸī
    -0.15
     μην
    -0.14
    elf
    -0.14
    isy
    -0.14
    POSITIVE LOGITS
    puts
    0.29
    ought
    0.28
    ly
    0.28
    ogh
    0.27
    -out
    0.27
    put
    0.27
    out
    0.26
    bred
    0.23
    OUT
    0.23
    LY
    0.21
    Act Density 0.084%

    No Known Activations