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

    Neuronpedia

    INDEX
    Explanations

    references to various conditions or states of being related to empty or missing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hausen
    -0.18
    olars
    -0.16
     Gat
    -0.14
     sever
    -0.14
     major
    -0.14
     harmon
    -0.14
     depending
    -0.14
    -ar
    -0.13
    ajor
    -0.13
    elle
    -0.13
    POSITIVE LOGITS
    itsu
    0.18
    >,</
    0.17
    bew
    0.15
     Lever
    0.15
     ===>
    0.15
    å±ĭ
    0.14
    лий
    0.14
    rug
    0.14
    ITERAL
    0.14
     Wolff
    0.14
    Act Density 0.020%

    No Known Activations