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

    Neuronpedia

    INDEX
    Explanations

    strong descriptors or references to strength in various contexts

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

    "strong" and its related forms

    np_acts-logits-general · gemini-2.0-flash

    strong and weak descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.58
     betweenstory
    -0.57
     Tripura
    -0.57
     myſelf
    -0.56
    djangoproject
    -0.56
     hablamos
    -0.56
     urbanas
    -0.56
    ANEOUS
    -0.56
    yntaxException
    -0.55
     felizes
    -0.54
    POSITIVE LOGITS
    STRONG
    1.03
     Weak
    0.98
     Strong
    0.93
     weak
    0.92
    strong
    0.92
    Strong
    0.91
    weak
    0.90
     STRONG
    0.88
     willed
    0.83
    Weak
    0.83
    Act Density 0.090%

    No Known Activations