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

    Neuronpedia

    INDEX
    Explanations

    terms related to intensity and intensive processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rial
    -0.16
    osen
    -0.15
    TES
    -0.15
    sworth
    -0.14
    abra
    -0.14
    703
    -0.14
    isper
    -0.14
    illus
    -0.14
    tes
    -0.14
    imension
    -0.13
    POSITIVE LOGITS
    /ext
    0.20
    ently
    0.18
    razione
    0.17
    ively
    0.16
    -duty
    0.16
    isty
    0.16
     scrutiny
    0.15
     kali
    0.15
    ening
    0.15
    eing
    0.15
    Act Density 0.016%

    No Known Activations