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

    Neuronpedia

    INDEX
    Explanations

    specific legal terms related to procedures and selections

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to selection and procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itar
    -0.72
     Shinra
    -0.66
    otten
    -0.65
    ian
    -0.64
    Tes
    -0.63
    nexus
    -0.62
    aurus
    -0.62
    rpm
    -0.62
    ARB
    -0.62
    cius
    -0.61
    POSITIVE LOGITS
     Selected
    1.07
    irlf
    0.71
    println
    0.70
     arrang
    0.67
     nervously
    0.64
     exha
    0.63
     collaborator
    0.62
    WORK
    0.62
    ookie
    0.62
    cffff
    0.61
    Act Density 0.001%

    No Known Activations