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

    Neuronpedia

    INDEX
    Explanations

    words related to strength or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.65
    djangoproject
    -0.64
     виправивши
    -0.60
     مرئيه
    -0.60
    justed
    -0.58
    yntaxException
    -0.57
     betweenstory
    -0.57
     Tripura
    -0.56
    ℚ
    -0.56
     resourceCulture
    -0.56
    POSITIVE LOGITS
     Strong
    1.17
    STRONG
    1.16
    strong
    1.14
    Strong
    1.14
     strong
    1.11
     Weak
    1.07
     STRONG
    1.06
     weak
    1.02
     stronger
    1.01
    weak
    0.98
    Act Density 0.102%

    No Known Activations