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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" in various contexts, often associated with lists or combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cmds
    -0.15
    kip
    -0.15
    imar
    -0.14
     Preferred
    -0.14
     Swan
    -0.14
    FAULT
    -0.14
    ัมà¸ŀ
    -0.14
    onom
    -0.14
    unce
    -0.14
     Pig
    -0.13
    POSITIVE LOGITS
     alike
    0.17
    esi
    0.16
     lab
    0.15
    esome
    0.14
     import
    0.14
     agenda
    0.13
     thanh
    0.13
    å¹¹ç·ļ
    0.13
     Jame
    0.13
    jak
    0.13
    Act Density 0.227%

    No Known Activations