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

    Neuronpedia

    INDEX
    Explanations

    terms related to improvement and optimization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eu
    -0.16
    -picker
    -0.14
    resher
    -0.14
    .Unity
    -0.14
     Levine
    -0.14
    chooser
    -0.14
    fulness
    -0.14
    .Listener
    -0.14
     serialVersionUID
    -0.13
    rieg
    -0.13
    POSITIVE LOGITS
    /im
    0.16
    usat
    0.16
    /mit
    0.15
     effort
    0.15
    urette
    0.14
    /max
    0.14
     overall
    0.14
     efforts
    0.14
    alem
    0.14
    arin
    0.13
    Act Density 0.104%

    No Known Activations