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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "anything" and related phrases indicative of uncertainty or lack of specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑı
    -0.17
    032
    -0.16
    inya
    -0.15
     Spir
    -0.15
    yal
    -0.15
    034
    -0.14
     habit
    -0.14
    kili
    -0.14
     Barker
    -0.14
    emann
    -0.14
    POSITIVE LOGITS
    нки
    0.16
    виÑī
    0.15
    arf
    0.15
    ýt
    0.14
    conti
    0.14
    ÑĢÑĥÑĤ
    0.14
    ooks
    0.14
     arc
    0.14
     SAL
    0.14
    AIN
    0.14
    Act Density 0.262%

    No Known Activations