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

    Neuronpedia

    INDEX
    Explanations

    evaluative language related to quality and effectiveness

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

    "Well" followed by a positive adjective

    np_acts-logits-general · gemini-2.0-flash

    well followed by quality descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.61
    adillas
    -0.57
     متعلقه
    -0.57
    adecimal
    -0.57
     мәкал
    -0.56
    enumerable
    -0.54
    EditorBrowsable
    -0.54
    出版年
    -0.53
    gaged
    -0.53
    etcode
    -0.53
    POSITIVE LOGITS
     expertly
    1.32
     skillfully
    1.32
     cleverly
    1.30
     excellently
    1.27
     thoughtfully
    1.24
     nicely
    1.23
     intelligently
    1.21
     properly
    1.21
     beautifully
    1.19
     executed
    1.19
    Act Density 0.290%

    No Known Activations