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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sters
    -0.15
    ster
    -0.15
    uddy
    -0.15
    meld
    -0.14
    635
    -0.14
    uisse
    -0.14
    pedia
    -0.14
    indi
    -0.14
     shim
    -0.13
    rat
    -0.13
    POSITIVE LOGITS
    iges
    0.15
    ity
    0.14
     Invasion
    0.14
    çī
    0.14
    bum
    0.14
    laÅŁma
    0.13
    ẫn
    0.13
    toupper
    0.13
     Rack
    0.13
    ause
    0.13
    Act Density 0.310%

    No Known Activations