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

    Neuronpedia

    INDEX
    Explanations

    units and measurements typically used in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.51
     surla
    -0.49
     Ouverture
    -0.47
    lwjgl
    -0.46
    vač
    -0.45
     concier
    -0.45
    ʁ
    -0.45
    хьтан
    -0.44
     AttributeSet
    -0.44
    mber
    -0.43
    POSITIVE LOGITS
     contextLoads
    0.69
    انيف
    0.68
    帖最后由
    0.64
    Referencies
    0.63
    ⇑
    0.62
     noDo
    0.60
    RegressionTest
    0.59
     مشين
    0.59
     pâtes
    0.58
     חיצוניים
    0.58
    Act Density 0.023%

    No Known Activations