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

    Neuronpedia

    INDEX
    Explanations

    definitions or references related to the concept of "defining" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fac
    -0.17
    ittle
    -0.16
    achen
    -0.16
    entieth
    -0.15
    fields
    -0.15
    ach
    -0.15
    erot
    -0.15
    fit
    -0.15
    itten
    -0.15
    ipt
    -0.14
    POSITIVE LOGITS
     def
    0.31
     Def
    0.28
    -def
    0.28
    (def
    0.24
    initely
    0.22
    _Def
    0.22
    .Def
    0.21
    .def
    0.21
    rost
    0.21
    unct
    0.21
    Act Density 0.018%

    No Known Activations