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

    Neuronpedia

    INDEX
    Explanations

    references to clothing and attire

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

    attire, clothes, or being dressed

    np_acts-logits-general · gemini-2.0-flash

    attire and state of being nude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.56
    httphttps
    -0.53
    InjectAttribute
    -0.47
     précie
    -0.45
    kháu
    -0.44
    TypedDataSet
    -0.44
    +#+
    -0.44
     estabiliz
    -0.43
    pulseira
    -0.42
     auprès
    -0.42
    POSITIVE LOGITS
     dress
    0.86
     attire
    0.82
     clothing
    0.77
     Dress
    0.77
     clothes
    0.75
    Dress
    0.73
     clothed
    0.69
     garments
    0.69
     dressed
    0.68
     garb
    0.66
    Act Density 0.132%

    No Known Activations