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

    Neuronpedia

    INDEX
    Explanations

    acronyms and initialisms related to organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sink
    -0.16
    ãĥªãĥ¼ãĤº
    -0.16
    ãģ¾
    -0.16
     sink
    -0.14
     Editing
    -0.14
    recated
    -0.14
    jev
    -0.14
    tgt
    -0.14
     Kol
    -0.13
    ivism
    -0.13
    POSITIVE LOGITS
    idal
    0.15
    AILS
    0.14
    lice
    0.13
    coil
    0.13
    .AddParameter
    0.13
     Cần
    0.13
    phia
    0.13
    iffs
    0.13
    idth
    0.13
     sortOrder
    0.13
    Act Density 0.032%

    No Known Activations