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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or unpredictability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arak
    -0.16
    ismet
    -0.15
    неÑĤ
    -0.15
    utenberg
    -0.15
    ãĥ³ãĥķ
    -0.15
    cobra
    -0.14
    äºĪ
    -0.14
    erra
    -0.14
    _UC
    -0.14
    .gov
    -0.14
    POSITIVE LOGITS
    asty
    0.16
    ojÃŃ
    0.15
    ìļĶ
    0.15
     Huffman
    0.15
    ays
    0.14
    rud
    0.14
    azine
    0.14
     Tanner
    0.14
    ashi
    0.14
     pelic
    0.14
    Act Density 0.011%

    No Known Activations