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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of expression or conveying meaning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¡ĶãĤĴ
    -0.15
    ocol
    -0.15
    å¼ķãģį
    -0.14
    áÄį
    -0.14
     Tough
    -0.14
    imity
    -0.13
    ossa
    -0.13
    ptron
    -0.13
    bia
    -0.13
    mland
    -0.13
    POSITIVE LOGITS
     speaks
    0.38
     speak
    0.38
     volumes
    0.33
     speaking
    0.33
     Speak
    0.31
    spe
    0.29
     Spe
    0.29
    Speak
    0.29
     spoke
    0.29
    -speaking
    0.28
    Act Density 0.024%

    No Known Activations