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

    Neuronpedia

    INDEX
    Explanations

    references to specific guidelines and reports discussing policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agas
    -0.15
    extensions
    -0.14
    ate
    -0.14
     Micha
    -0.13
    ilon
    -0.13
     Iss
    -0.13
    ÑĮе
    -0.13
     shorts
    -0.13
    lane
    -0.13
    pton
    -0.13
    POSITIVE LOGITS
     page
    0.22
     nowhere
    0.20
     elsewhere
    0.20
     section
    0.20
     throughout
    0.19
    .page
    0.19
     passage
    0.19
     paragraph
    0.18
    第
    0.18
    (page
    0.18
    Act Density 0.282%

    No Known Activations