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

    Neuronpedia

    INDEX
    Explanations

    terms related to negative outcomes or impacts, particularly in performance contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    negative impact or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sterdam
    -0.44
     pione
    -0.40
     betweenstory
    -0.38
    WriteBarrier
    -0.37
     AssemblyTitle
    -0.37
    meiras
    -0.37
     children
    -0.37
    SAF
    -0.36
    </thead>
    -0.36
    RenderAtEndOf
    -0.36
    POSITIVE LOGITS
    BeginContext
    0.55
     impact
    0.51
     pinulongan
    0.50
     ModelExpression
    0.50
    تقاوى
    0.50
    ografija
    0.48
     perturbations
    0.47
     Impacts
    0.47
     boosts
    0.47
     Boost
    0.47
    Act Density 0.184%

    No Known Activations