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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty, casual expressions, and discussions of personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    мовÑĸÑĢ
    -0.19
     поÑģÑĤоÑıнно
    -0.16
    å¹¹
    -0.15
     ÑĤепеÑĢÑĮ
    -0.15
     unlikely
    -0.15
    ager
    -0.15
     ÅŁimdi
    -0.15
    .getColumnIndex
    -0.15
    EATURE
    -0.14
     siempre
    -0.14
    POSITIVE LOGITS
     sometimes
    0.27
     simply
    0.26
    Sometimes
    0.25
     Sometimes
    0.23
     Simply
    0.21
     even
    0.20
    sometimes
    0.20
     just
    0.19
    Simply
    0.18
     depending
    0.18
    Act Density 0.136%

    No Known Activations