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

    Neuronpedia

    INDEX
    Explanations

    terms related to improvement, enhancement, and increases in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @",
    -0.55
    otherwise
    -0.52
     Notting
    -0.50
    paque
    -0.50
    häng
    -0.50
     ≠
    -0.50
     OTHERWISE
    -0.50
    chließend
    -0.48
    setResult
    -0.47
     affatto
    -0.46
    POSITIVE LOGITS
     increase
    1.60
    increase
    1.47
    Increase
    1.43
     increased
    1.40
     Increase
    1.40
     increases
    1.38
     INCREASE
    1.35
    Increases
    1.34
     Increases
    1.33
     Increased
    1.28
    Act Density 0.672%

    No Known Activations