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

    Neuronpedia

    INDEX
    Explanations

    terms related to pooled data and its analysis

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

    pooled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tornillo
    -0.39
     contextLoads
    -0.36
     skj
    -0.35
    bootstrapcdn
    -0.35
     scientifiques
    -0.34
     entregas
    -0.34
     completion
    -0.34
     ennemi
    -0.34
     sainte
    -0.34
     skru
    -0.33
    POSITIVE LOGITS
     pooled
    1.56
     pooling
    1.53
     pool
    1.48
    pooling
    1.41
     Pool
    1.38
    pool
    1.36
    pooled
    1.34
     pools
    1.30
     POOL
    1.25
    Pooling
    1.20
    Act Density 0.022%

    No Known Activations