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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "rumor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ately
    -0.16
    zsche
    -0.15
    ucha
    -0.14
    obuf
    -0.14
    etsy
    -0.14
    ãĥ¼ãĤ
    -0.14
    cheng
    -0.14
    ãĥ¶
    -0.14
    stellung
    -0.14
    506
    -0.13
    POSITIVE LOGITS
     rum
    0.20
    ination
    0.20
    rum
    0.19
    mers
    0.19
    untu
    0.17
     Rum
    0.16
    ple
    0.16
    inate
    0.15
    ECTOR
    0.15
    pled
    0.15
    Act Density 0.006%

    No Known Activations