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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer hardware and software functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gay
    -0.15
    WithData
    -0.15
    ahy
    -0.14
    ãģİ
    -0.14
    /backend
    -0.14
     Cour
    -0.14
    lesia
    -0.14
    Uvs
    -0.14
    mur
    -0.13
    GBK
    -0.13
    POSITIVE LOGITS
     mode
    0.21
    -mode
    0.19
     Mode
    0.18
     Modes
    0.17
     modes
    0.17
    emode
    0.16
    mode
    0.16
     ActionTypes
    0.16
    Mode
    0.15
    rik
    0.15
    Act Density 0.211%

    No Known Activations