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

    Neuronpedia

    INDEX
    Explanations

    terms indicating statistical significance or notable findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CYCLE
    -0.42
     AUTOM
    -0.40
     ateliers
    -0.40
    ipur
    -0.40
    sprache
    -0.39
    izhou
    -0.39
     Edo
    -0.39
     types
    -0.39
     Myself
    -0.39
     ato
    -0.39
    POSITIVE LOGITS
     Significant
    1.70
    Significant
    1.69
     significant
    1.61
    significant
    1.56
     substantial
    1.28
     Substantial
    1.27
     significativa
    1.27
     significativo
    1.26
     SIGNIFIC
    1.26
     considerable
    1.23
    Act Density 0.328%

    No Known Activations