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

    Neuronpedia

    INDEX
    Explanations

    terms related to improvement or enhancement in various contexts

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

    Sentences about making something better

    np_acts-logits-general · gemini-2.0-flash

    improve followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CardHeader
    -0.51
    dchen
    -0.48
    RetentionPolicy
    -0.47
     telegram
    -0.46
     BorderRadius
    -0.45
    DataMember
    -0.45
     Palacios
    -0.44
     braccia
    -0.44
     Gabel
    -0.44
    olella
    -0.44
    POSITIVE LOGITS
    improve
    1.63
     improve
    1.57
     Improve
    1.56
     improvement
    1.56
    Improve
    1.55
    improvement
    1.55
    improving
    1.54
    improved
    1.53
     Improvement
    1.53
     improved
    1.53
    Act Density 0.129%

    No Known Activations