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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references related to programming and software engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubo
    -0.17
     Mane
    -0.17
    Manip
    -0.16
    Accessor
    -0.16
    ippi
    -0.16
     Manip
    -0.15
     accessor
    -0.15
    estroy
    -0.15
    loat
    -0.14
    uve
    -0.14
    POSITIVE LOGITS
     recognizes
    0.28
     recognize
    0.27
     detect
    0.26
     detects
    0.26
     recognise
    0.26
     automatically
    0.25
     treat
    0.25
     recogn
    0.24
     automatic
    0.24
     detecting
    0.23
    Act Density 0.169%

    No Known Activations