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

    Neuronpedia

    INDEX
    Explanations

    terms related to increasing or enhancing performance or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.77
     '\\;'
    -0.70
    HttpFoundation
    -0.67
    пія
    -0.63
    istoitu
    -0.63
    rungsseite
    -0.63
    illoma
    -0.61
    bkz
    -0.61
    migrationBuilder
    -0.60
     CommonModule
    -0.60
    POSITIVE LOGITS
     boost
    1.23
     Boost
    1.14
    Boost
    1.13
     boosts
    1.09
     boosting
    1.09
    boost
    1.08
     BOOST
    1.04
    BOOST
    0.82
     boosted
    0.80
    osted
    0.78
    Act Density 0.057%

    No Known Activations